Pyriamds3

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2b5968996ca30102e07382d4495d24d72ec175443a72e92747b351b14f4e75a
+oid sha256:59e25a44f49c6d5a97f004836b5a3c096c7295120d999d5c2ab2f0d4ef86677f
 size 1418184

Pyramids/Pyramids-10499989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6426d8692c7893fd7450b5cf77d2ae7c52d16065fd4baa87beff25bb90a38f
+size 1418184

Pyramids/Pyramids-10499989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bab4a09ae333f77ce906d19807e36d23ef25a57d006fd1f0fa9825802b884b9c
+size 8650990

Pyramids/Pyramids-10999990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:381d9835f46748f6b46704b28104170753b9db6ab43444fa7d4ac0c3b853d641
+size 1418184

Pyramids/Pyramids-10999990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:689f6d8c61d1616a7880a8dad1ab8776d7895f066236af2967bd09be7affe0e4
+size 8650990

Pyramids/Pyramids-11314051.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e25a44f49c6d5a97f004836b5a3c096c7295120d999d5c2ab2f0d4ef86677f
+size 1418184

Pyramids/Pyramids-11314051.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4659c9a9935a28d203187765162c37a93d9b7b51a95f625309ebcdcd5f9890df
+size 8650990

Pyramids/Pyramids-60195.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c20cba3591acc518a4afe7b060d37b3fcf7f4ee8c810586784f2825b8c380a
+size 1418184

Pyramids/Pyramids-60195.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f81f035f78cc1026d9c225242bbbd29f3ee3d6fda8e5e7e95238e9cd031c3c
+size 8650990

Pyramids/Pyramids-9499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17ffbbf4cfb8109d3cce3f15a0f523dfef5af33858f680a6c9c1c7725f0006ed
+size 1418184

Pyramids/Pyramids-9499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb3e930f3da3a6f7b22968f4a3b22c9db5be359c3d9cf82f5ae66865d05d3c3
+size 8650990

Pyramids/Pyramids-9999965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75ecf56436ef56517176792c77a53ee9859a41dd252ea261bb988e8b459d8825
+size 1418184

Pyramids/Pyramids-9999965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d045aa4e475978964a5cb4aebbfabc0bd7e379cc647ba8aa7070002437f65260
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c951bc0fc2a8eb8862bae09c2d752d97a2c1c918922878dd1f17b937cfb04ac
+oid sha256:4659c9a9935a28d203187765162c37a93d9b7b51a95f625309ebcdcd5f9890df
 size 8650990

Pyramids/events.out.tfevents.1689757961.arran.698557.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f6ad9073b32a213aa4c68cf48220f03c8d52714fe37bb0ff36d78af72578ce
+size 3637051

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 256, "buffer_size": 4096, "learning_rate": 0.003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -3,9 +3,9 @@ behaviors:
   Pyramids:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
+      batch_size: 256
+      buffer_size: 4096
+      learning_rate: 0.003
       beta: 0.01
       epsilon: 0.2
       lambd: 0.95
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 50000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
-Found 3 interfaces on host : 0) 192.168.8.122 1) 172.17.0.1 2) 192.168.176.1
-Multi-casting "[IP] 192.168.8.122 [Port] 55502 [Flags] 2 [Guid] 1661159740 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.8.122) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Found 4 interfaces on host : 0) 192.168.8.122 1) 172.17.0.1 2) 192.168.176.1 3) 10.212.134.120
+Multi-casting "[IP] 192.168.8.122 [Port] 55358 [Flags] 2 [Guid] 3569147886 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.212.134.120) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -13,7 +13,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.061 seconds
+- Completed reload, in  0.053 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -45,7 +45,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.440596 ms
+UnloadTime: 0.484780 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 8 worker threads for Enlighten.
@@ -53,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 28431 frames, [32.0 KB-64.0 KB]: 92320 frames, [64.0 KB-128.0 KB]: 66762 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 28619 frames, [32.0 KB-64.0 KB]: 128165 frames, [64.0 KB-128.0 KB]: 55376 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -161,7 +161,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
@@ -208,6 +208,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -218,14 +223,14 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_EnlightenWorker] x 8
@@ -236,12 +241,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 9]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 7]
       Initial Block Size 256.0 KB
@@ -254,28 +254,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 187215 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 211862 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11919
+  Peak main deferred allocation count 11949
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.8 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 187513 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 212160 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.3 MB
+      Peak Allocated memory 30.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 187514 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 212161 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 27.8 MB
+      Peak Allocated memory 29.0 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -304,13 +304,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.8 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 187513 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 212160 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 187514 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 212161 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -322,13 +322,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.8 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 187215 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 211862 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 187513 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 212160 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -340,19 +340,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.8 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 187514 frames
+      Peak usage frame count: [0-1.0 KB]: 212161 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 187514 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 212161 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.9 KB
       Peak Large allocation bytes 0 B
 [ALLOC_PROFILER]
-  Peak usage frame count: [32.0 KB-64.0 KB]: 187514 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 212161 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 38.5 KB
@@ -361,4 +361,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1689718048070,"processId":455655,"allocatedMemory":2177431,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":206054},{"Thread":34852},{"Manager":18447},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3544},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1689767774381,"processId":698617,"allocatedMemory":2177431,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":206054},{"Thread":34852},{"Manager":18447},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3544},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.0955950915813446,
-            "min": 0.09436549991369247,
-            "max": 1.3554917573928833,
-            "count": 333
+            "value": 0.4197154641151428,
+            "min": 0.272203266620636,
+            "max": 1.5045830011367798,
+            "count": 377
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 2840.3212890625,
-            "min": 2833.984619140625,
-            "max": 41120.19921875,
-            "count": 333
+            "value": 12625.041015625,
+            "min": 8148.67724609375,
+            "max": 45643.03125,
+            "count": 377
         },
         "Pyramids.Step.mean": {
-            "value": 9989901.0,
-            "min": 29980.0,
-            "max": 9989901.0,
-            "count": 333
+            "value": 11309921.0,
+            "min": 29952.0,
+            "max": 11309921.0,
+            "count": 377
         },
         "Pyramids.Step.sum": {
-            "value": 9989901.0,
-            "min": 29980.0,
-            "max": 9989901.0,
-            "count": 333
+            "value": 11309921.0,
+            "min": 29952.0,
+            "max": 11309921.0,
+            "count": 377
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.9043908715248108,
-            "min": -0.11052733659744263,
-            "max": 0.9892714023590088,
-            "count": 333
+            "value": 0.7003707885742188,
+            "min": -0.19950847327709198,
+            "max": 0.7662648558616638,
+            "count": 377
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 283.0743408203125,
-            "min": -26.637088775634766,
-            "max": 315.57757568359375,
-            "count": 333
+            "value": 197.5045623779297,
+            "min": -47.28350830078125,
+            "max": 224.49522399902344,
+            "count": 377
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.004980965051800013,
-            "min": -0.045170947909355164,
-            "max": 0.6073437929153442,
-            "count": 333
+            "value": 0.003947226796299219,
+            "min": -0.05940214917063713,
+            "max": 0.3908889889717102,
+            "count": 377
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.5590420961380005,
-            "min": -13.280258178710938,
-            "max": 144.54782104492188,
-            "count": 333
+            "value": 1.1131179332733154,
+            "min": -16.513797760009766,
+            "max": 93.8133544921875,
+            "count": 377
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06626909062227546,
-            "min": 0.06334194002279435,
-            "max": 0.07505433494494172,
-            "count": 333
+            "value": 0.05026319106469773,
+            "min": 0.04300903675833806,
+            "max": 0.09981689124556614,
+            "count": 377
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9277672687118563,
-            "min": 0.5652185566612553,
-            "max": 1.08269119888713,
-            "count": 333
+            "value": 0.3518423374528841,
+            "min": 0.2035083431895173,
+            "max": 0.698718238718963,
+            "count": 377
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.013294236297952013,
-            "min": 0.0004800667355683263,
-            "max": 0.022125206542101213,
-            "count": 333
+            "value": 0.01388661854296169,
+            "min": 0.00031933543865666705,
+            "max": 9.80639659676568,
+            "count": 377
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.18611930817132818,
-            "min": 0.0062408675623882425,
-            "max": 0.24089624340801188,
-            "count": 333
+            "value": 0.09720632980073182,
+            "min": 0.0022353480705966694,
+            "max": 68.64477617735976,
+            "count": 377
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.286390428678534e-07,
-            "min": 7.286390428678534e-07,
-            "max": 0.00029952244515918494,
-            "count": 333
+            "value": 0.002322299456875733,
+            "min": 0.002322299456875733,
+            "max": 0.0029990899200303357,
+            "count": 377
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 1.0200946600149948e-05,
-            "min": 1.0200946600149948e-05,
-            "max": 0.004169206010264699,
-            "count": 333
+            "value": 0.01625609619813013,
+            "min": 0.011996359680121343,
+            "max": 0.02384890956503635,
+            "count": 377
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10024284642857142,
-            "min": 0.10024284642857142,
-            "max": 0.199840815,
-            "count": 333
+            "value": 0.17740998114285714,
+            "min": 0.17740998114285714,
+            "max": 0.19996966400000002,
+            "count": 377
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.40339985,
-            "min": 1.40339985,
-            "max": 2.8897353000000003,
-            "count": 333
+            "value": 1.241869868,
+            "min": 0.7998786560000001,
+            "max": 1.5949636520000001,
+            "count": 377
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 3.4260358214285587e-05,
-            "min": 3.4260358214285587e-05,
-            "max": 0.0099840974185,
-            "count": 333
+            "value": 0.007743257116171428,
+            "min": 0.007743257116171428,
+            "max": 0.0099969694336,
+            "count": 377
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0004796450149999982,
-            "min": 0.0004796450149999982,
-            "max": 0.13898455647,
-            "count": 333
+            "value": 0.054202799813199996,
+            "min": 0.0399878777344,
+            "max": 0.0794968688348,
+            "count": 377
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00384402833878994,
-            "min": 0.0037226839922368526,
-            "max": 0.6547409296035767,
-            "count": 333
+            "value": 0.0034704941790550947,
+            "min": 0.0034704941790550947,
+            "max": 0.6667643785476685,
+            "count": 377
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.05381639674305916,
-            "min": 0.05211757495999336,
-            "max": 5.237927436828613,
-            "count": 333
+            "value": 0.024293459951877594,
+            "min": 0.024293459951877594,
+            "max": 2.667057514190674,
+            "count": 377
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 187.03821656050957,
-            "min": 163.06989247311827,
+            "value": 316.0,
+            "min": 237.55371900826447,
             "max": 999.0,
-            "count": 333
+            "count": 377
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29365.0,
-            "min": 15884.0,
-            "max": 33758.0,
-            "count": 333
+            "value": 30968.0,
+            "min": 15984.0,
+            "max": 35843.0,
+            "count": 377
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.8002203718112533,
-            "min": -0.9999806972280625,
-            "max": 1.8370540386116183,
-            "count": 333
+            "value": 1.644698966482673,
+            "min": -1.0000000521540642,
+            "max": 1.7624462644669636,
+            "count": 377
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 282.63459837436676,
-            "min": -30.99940161406994,
-            "max": 339.8549971431494,
-            "count": 333
+            "value": 162.82519768178463,
+            "min": -29.995001636445522,
+            "max": 218.6787971407175,
+            "count": 377
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.8002203718112533,
-            "min": -0.9999806972280625,
-            "max": 1.8370540386116183,
-            "count": 333
+            "value": 1.644698966482673,
+            "min": -1.0000000521540642,
+            "max": 1.7624462644669636,
+            "count": 377
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 282.63459837436676,
-            "min": -30.99940161406994,
-            "max": 339.8549971431494,
-            "count": 333
+            "value": 162.82519768178463,
+            "min": -29.995001636445522,
+            "max": 218.6787971407175,
+            "count": 377
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.00748890871219159,
-            "min": 0.006728075081411737,
-            "max": 15.630076319095679,
-            "count": 333
+            "value": 0.011586302707398475,
+            "min": 0.009915739200480927,
+            "max": 11.432586884126067,
+            "count": 377
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.1757586678140797,
-            "min": 1.1340146101138089,
-            "max": 250.08122110553086,
-            "count": 333
+            "value": 1.147043968032449,
+            "min": 1.0746353828071733,
+            "max": 182.92139014601707,
+            "count": 377
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 333
+            "count": 377
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 333
+            "count": 377
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1689708856",
+        "start_time_seconds": "1689757960",
         "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
         "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1689718048"
+        "end_time_seconds": "1689767774"
     },
-    "total": 9191.136063812999,
+    "total": 9813.438060935005,
     "count": 1,
-    "self": 0.21783762199629564,
+    "self": 0.14997585001401603,
     "children": {
         "run_training.setup": {
-            "total": 0.009290647998568602,
+            "total": 0.009300467994762585,
             "count": 1,
-            "self": 0.009290647998568602
+            "self": 0.009300467994762585
         },
         "TrainerController.start_learning": {
-            "total": 9190.908935543004,
+            "total": 9813.278784616996,
             "count": 1,
-            "self": 7.296172509493772,
+            "self": 9.232576190959662,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2592835880059283,
+                    "total": 2.422013842005981,
                     "count": 1,
-                    "self": 2.2592835880059283
+                    "self": 2.422013842005981
                 },
                 "TrainerController.advance": {
-                    "total": 9181.289401419504,
-                    "count": 658089,
-                    "self": 6.706666782862158,
+                    "total": 9801.555481683026,
+                    "count": 732625,
+                    "self": 8.413826392206829,
                     "children": {
                         "env_step": {
-                            "total": 5506.038501513656,
-                            "count": 658089,
-                            "self": 4669.653360345765,
+                            "total": 6327.068002251006,
+                            "count": 732625,
+                            "self": 5318.326892920915,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 831.8433572594222,
-                                    "count": 658089,
-                                    "self": 21.683317840346717,
+                                    "total": 1003.0577777927683,
+                                    "count": 732625,
+                                    "self": 25.714818801294314,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 810.1600394190755,
-                                            "count": 625044,
-                                            "self": 810.1600394190755
+                                            "total": 977.342958991474,
+                                            "count": 707201,
+                                            "self": 977.342958991474
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 4.54178390846937,
-                                    "count": 658089,
+                                    "total": 5.683331537322374,
+                                    "count": 732624,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 9181.73563117189,
-                                            "count": 658089,
+                                            "total": 9801.626357703004,
+                                            "count": 732624,
                                             "is_parallel": true,
-                                            "self": 4984.935508643743,
+                                            "self": 5066.491318356275,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.000965316008660011,
+                                                            "total": 0.0007869589899200946,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002711040433496237,
+                                                            "self": 0.00021948496578261256,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006942119653103873,
+                                                                    "total": 0.000567474024137482,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006942119653103873
+                                                                    "self": 0.000567474024137482
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.01789177200407721,
+                                                            "total": 0.01652249798644334,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00021794400527141988,
+                                                            "self": 0.00017548198229633272,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00022436400467995554,
+                                                                    "total": 0.00020307398517616093,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00022436400467995554
+                                                                    "self": 0.00020307398517616093
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.01678669999819249,
+                                                                    "total": 0.015603690000716597,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.01678669999819249
+                                                                    "self": 0.015603690000716597
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006627639959333465,
+                                                                    "total": 0.0005402520182542503,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00015804098802618682,
+                                                                    "self": 0.00013721000868827105,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005047230079071596,
+                                                                            "total": 0.00040304200956597924,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005047230079071596
+                                                                            "self": 0.00040304200956597924
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 4196.800122528148,
-                                                    "count": 658088,
+                                                    "total": 4735.135039346729,
+                                                    "count": 732623,
                                                     "is_parallel": true,
-                                                    "self": 126.31859621261538,
+                                                    "self": 148.83361234873882,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 91.8040517183108,
-                                                            "count": 658088,
+                                                            "total": 108.86860577567131,
+                                                            "count": 732623,
                                                             "is_parallel": true,
-                                                            "self": 91.8040517183108
+                                                            "self": 108.86860577567131
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 3603.8484257075324,
-                                                            "count": 658088,
+                                                            "total": 4039.3383600350353,
+                                                            "count": 732623,
                                                             "is_parallel": true,
-                                                            "self": 3603.8484257075324
+                                                            "self": 4039.3383600350353
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 374.82904888968915,
-                                                            "count": 658088,
+                                                            "total": 438.09446118728374,
+                                                            "count": 732623,
                                                             "is_parallel": true,
-                                                            "self": 83.5557382828265,
+                                                            "self": 100.58675679168664,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 291.27331060686265,
-                                                                    "count": 5264704,
+                                                                    "total": 337.5077043955971,
+                                                                    "count": 5860984,
                                                                     "is_parallel": true,
-                                                                    "self": 291.27331060686265
+                                                                    "self": 337.5077043955971
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 3668.544233122986,
-                            "count": 658089,
-                            "self": 13.930175016677822,
+                            "total": 3466.0736530398135,
+                            "count": 732624,
+                            "self": 16.990142274677055,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 710.9470578132459,
-                                    "count": 658089,
-                                    "self": 709.6599365632719,
+                                    "total": 817.632784697169,
+                                    "count": 732624,
+                                    "self": 816.1766611461062,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2871212499740068,
-                                            "count": 20,
-                                            "self": 1.2871212499740068
+                                            "total": 1.456123551062774,
+                                            "count": 22,
+                                            "self": 1.456123551062774
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 2943.6670002930623,
-                                    "count": 4716,
-                                    "self": 1794.112542707604,
+                                    "total": 2631.4507260679675,
+                                    "count": 2712,
+                                    "self": 1861.5610947568202,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 1149.5544575854583,
-                                            "count": 227982,
-                                            "self": 1149.5544575854583
+                                            "total": 769.8896313111472,
+                                            "count": 130515,
+                                            "self": 769.8896313111472
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.110050551593304e-07,
+                    "total": 6.709888111799955e-07,
                     "count": 1,
-                    "self": 5.110050551593304e-07
+                    "self": 6.709888111799955e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.06407751499500591,
+                    "total": 0.06871223001508042,
                     "count": 1,
-                    "self": 0.001261867000721395,
+                    "self": 0.0009454120299778879,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.06281564799428452,
+                            "total": 0.06776681798510253,
                             "count": 1,
-                            "self": 0.06281564799428452
+                            "self": 0.06776681798510253
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 8499897,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-8499897.onnx",
-                "reward": 1.8573333074649174,
-                "creation_time": 1689716652.801483,
+                "steps": 9499994,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9499994.onnx",
+                "reward": 1.6714999869465827,
+                "creation_time": 1689766192.9233167,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-8499897.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-9499994.pt"
                 ]
             },
             {
-                "steps": 8999993,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-8999993.onnx",
-                "reward": 1.6949999630451202,
-                "creation_time": 1689717117.7614775,
+                "steps": 9999965,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9999965.onnx",
+                "reward": 1.7446666583418846,
+                "creation_time": 1689766635.719309,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-8999993.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-9999965.pt"
                 ]
             },
             {
-                "steps": 9499898,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9499898.onnx",
-                "reward": 1.798846150820072,
-                "creation_time": 1689717581.5694518,
+                "steps": 10499989,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-10499989.onnx",
+                "reward": 1.558892283302087,
+                "creation_time": 1689767063.2139647,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-9499898.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-10499989.pt"
                 ]
             },
             {
-                "steps": 9999901,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9999901.onnx",
-                "reward": null,
-                "creation_time": 1689718047.821493,
+                "steps": 10999990,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-10999990.onnx",
+                "reward": 1.4029999375343323,
+                "creation_time": 1689767498.6312547,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-9999901.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-10999990.pt"
                 ]
             },
             {
-                "steps": 10000029,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-10000029.onnx",
-                "reward": null,
-                "creation_time": 1689718047.891404,
+                "steps": 11314051,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-11314051.onnx",
+                "reward": 1.8064615233586385,
+                "creation_time": 1689767774.2427285,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-10000029.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-11314051.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 10000029,
+            "steps": 11314051,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1689718047.891404,
+            "reward": 1.8064615233586385,
+            "creation_time": 1689767774.2427285,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-10000029.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-11314051.pt"
             ]
         }
     },