Pyramids 2

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a67e29e833da1e657a85ea43d684be1624d66483936098f1715040c90cbc10
+oid sha256:eadd52c68d4916976eb6da334c69ac2cc51190283fb24d787c10cc30d3993ad0
 size 1417437

Pyramids/{Pyramids-499931.onnx → Pyramids-1000082.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a67e29e833da1e657a85ea43d684be1624d66483936098f1715040c90cbc10
+oid sha256:eadd52c68d4916976eb6da334c69ac2cc51190283fb24d787c10cc30d3993ad0
 size 1417437

Pyramids/{Pyramids-499931.pt → Pyramids-1000082.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb761b48e071bbd14bcfd667f5e173db658853e910d7b1e680c5693c4491c5f
+oid sha256:28cc430e3ef1b9f8e46baa1aa8644e0a57903ec0b16d4a35bbd22b2c9b5cfc45
 size 8652382

Pyramids/{Pyramids-500059.onnx → Pyramids-499954.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a67e29e833da1e657a85ea43d684be1624d66483936098f1715040c90cbc10
+oid sha256:9a70d8daeb98f0460ad3c0918de3159ff1775f8f5722e0b3ec3670fef2784ee3
 size 1417437

Pyramids/{Pyramids-500059.pt → Pyramids-499954.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc00248bbde0044fec74dc90fcf6ef88e9326cc6651e1d8cfcc0f3fba2dce06a
+oid sha256:5cbefbaea0c71af6bf564708b79220084ec21a7ea3891a8e25306907034b96f7
 size 8652382

Pyramids/Pyramids-999954.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadd52c68d4916976eb6da334c69ac2cc51190283fb24d787c10cc30d3993ad0
+size 1417437

Pyramids/Pyramids-999954.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec19f7febc8dab05701f9ff4354849f7c5aa34e1b3c4e781e0291ba1b2244dba
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc00248bbde0044fec74dc90fcf6ef88e9326cc6651e1d8cfcc0f3fba2dce06a
+oid sha256:28cc430e3ef1b9f8e46baa1aa8644e0a57903ec0b16d4a35bbd22b2c9b5cfc45
 size 8652382

Pyramids/{events.out.tfevents.1660495725.c728ff943ef5.271.0 → events.out.tfevents.1660498576.c728ff943ef5.914.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1ca1775ac1b8ee0b6369b21d695c0f4c5d5059f633736610cb5ca6dafc4d30
-size 147475
+oid sha256:3e39e983ed83f8423a0d06bef8e6ee95c045c8e17ce544b3e79c77fc8c3c04dd
+size 332978

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-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": false, "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": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-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_2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids_Training_2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55178 [Flags] 2 [Guid] 277572251 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55100 [Flags] 2 [Guid] 2723430613 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.090 seconds
+- Completed reload, in  0.092 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)
@@ -68,7 +65,7 @@ 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: 1.036920 ms
+UnloadTime: 0.902077 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 1 worker threads for Enlighten.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 5118 frames, [32.0 KB-64.0 KB]: 3703 frames, [64.0 KB-128.0 KB]: 574 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3936 frames, [32.0 KB-64.0 KB]: 12111 frames, [64.0 KB-128.0 KB]: 2719 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
@@ -126,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -136,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       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_Background Job.Worker 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ 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]: 9097 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12215
+  Peak main deferred allocation count 11560
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9395 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.5 MB
+      Peak Allocated memory 30.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9396 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.8 MB
+      Peak Allocated memory 22.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9395 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18766 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]: 9396 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18767 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9097 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18468 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]: 9395 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18766 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
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9396 frames
+      Peak usage frame count: [0-1.0 KB]: 18767 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]: 9396 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18767 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: [16.0 KB-32.0 KB]: 9396 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18767 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ 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":1660496796160,"processId":282,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"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":3444},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"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":1660500947565,"processId":925,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"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":3444},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6744004487991333,
-            "min": 0.6279477477073669,
-            "max": 1.4389331340789795,
-            "count": 16
+            "value": 0.3996748626232147,
+            "min": 0.3917907178401947,
+            "max": 1.4083820581436157,
+            "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 20242.8046875,
-            "min": 18808.291015625,
-            "max": 43651.4765625,
-            "count": 16
+            "value": 11696.0849609375,
+            "min": 11696.0849609375,
+            "max": 42724.6796875,
+            "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 479949.0,
-            "min": 29911.0,
-            "max": 479949.0,
-            "count": 16
+            "value": 989977.0,
+            "min": 29952.0,
+            "max": 989977.0,
+            "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 479949.0,
-            "min": 29911.0,
-            "max": 479949.0,
-            "count": 16
+            "value": 989977.0,
+            "min": 29952.0,
+            "max": 989977.0,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.07185470312833786,
-            "min": -0.17655961215496063,
-            "max": -0.04350561648607254,
-            "count": 16
+            "value": 0.4239376187324524,
+            "min": -0.1062420904636383,
+            "max": 0.5268458127975464,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -17.388837814331055,
-            "min": -41.844627380371094,
-            "max": -10.484853744506836,
-            "count": 16
+            "value": 112.76740264892578,
+            "min": -25.60434341430664,
+            "max": 143.8289031982422,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.025986438617110252,
-            "min": 0.025986438617110252,
-            "max": 0.5183269381523132,
-            "count": 16
+            "value": -0.04132157936692238,
+            "min": -0.04132157936692238,
+            "max": 0.49755334854125977,
+            "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.288718223571777,
-            "min": 6.288718223571777,
-            "max": 122.84349060058594,
-            "count": 16
+            "value": -10.99153995513916,
+            "min": -10.99153995513916,
+            "max": 117.9201431274414,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0664786800839162,
-            "min": 0.0660214240548484,
-            "max": 0.07667070973129948,
-            "count": 16
+            "value": 0.07135915358114533,
+            "min": 0.06495114032891468,
+            "max": 0.07678236405468969,
+            "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9971802012587432,
-            "min": 0.5366949681190963,
-            "max": 0.9971802012587432,
-            "count": 16
+            "value": 0.9990281501360346,
+            "min": 0.5129710693451263,
+            "max": 1.0623165880370993,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0010628796029239765,
-            "min": 8.687094145246701e-05,
-            "max": 0.015348110088629397,
-            "count": 16
+            "value": 0.015244013472839784,
+            "min": 0.0006924092753811993,
+            "max": 0.016371411484882532,
+            "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.015943194043859646,
-            "min": 0.0011293222388820711,
-            "max": 0.10743677062040578,
-            "count": 16
+            "value": 0.21341618861975697,
+            "min": 0.008308911304574392,
+            "max": 0.22919976078835547,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.1031012989693328e-05,
-            "min": 2.1031012989693328e-05,
-            "max": 0.00029046934603402854,
-            "count": 16
+            "value": 7.366318973164286e-06,
+            "min": 7.366318973164286e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0003154651948453999,
-            "min": 0.0003154651948453999,
-            "max": 0.0030081042972986,
-            "count": 16
+            "value": 0.0001031284656243,
+            "min": 0.0001031284656243,
+            "max": 0.0033829916723362,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1070103066666667,
-            "min": 0.1070103066666667,
-            "max": 0.19682311428571433,
-            "count": 16
+            "value": 0.10245540714285714,
+            "min": 0.10245540714285714,
+            "max": 0.19838354285714285,
+            "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.6051546000000003,
-            "min": 1.3777618000000003,
-            "max": 2.1504756,
-            "count": 16
+            "value": 1.4343757,
+            "min": 1.3886848,
+            "max": 2.5276638,
+            "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.000710329636,
-            "min": 0.000710329636,
-            "max": 0.009682629117142858,
-            "count": 16
+            "value": 0.00025529517357142855,
+            "min": 0.00025529517357142855,
+            "max": 0.00983851593142857,
+            "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.010654944539999999,
-            "min": 0.010654944539999999,
-            "max": 0.10027986986000001,
-            "count": 16
+            "value": 0.00357413243,
+            "min": 0.00357413243,
+            "max": 0.11279361362000001,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.023155469447374344,
-            "min": 0.023155469447374344,
-            "max": 0.5172693729400635,
-            "count": 16
+            "value": 0.009308808483183384,
+            "min": 0.008972725830972195,
+            "max": 0.6597505807876587,
+            "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.34733203053474426,
-            "min": 0.34733203053474426,
-            "max": 3.6208856105804443,
-            "count": 16
+            "value": 0.13032332062721252,
+            "min": 0.12561815977096558,
+            "max": 4.6182541847229,
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 985.6875,
-            "min": 921.3714285714286,
+            "value": 384.7837837837838,
+            "min": 373.4736842105263,
             "max": 999.0,
-            "count": 16
+            "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31542.0,
-            "min": 16582.0,
-            "max": 32633.0,
-            "count": 16
+            "value": 28474.0,
+            "min": 15984.0,
+            "max": 33089.0,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.8613000512123108,
+            "value": 1.4822273778997055,
             "min": -1.0000000521540642,
-            "max": -0.6297937964554876,
-            "count": 16
+            "max": 1.521226296691518,
+            "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -27.561601638793945,
-            "min": -31.00000161677599,
-            "max": -14.598000824451447,
-            "count": 16
+            "value": 108.2025985866785,
+            "min": -30.580801755189896,
+            "max": 120.74119840562344,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.8613000512123108,
+            "value": 1.4822273778997055,
             "min": -1.0000000521540642,
-            "max": -0.6297937964554876,
-            "count": 16
+            "max": 1.521226296691518,
+            "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -27.561601638793945,
-            "min": -31.00000161677599,
-            "max": -14.598000824451447,
-            "count": 16
+            "value": 108.2025985866785,
+            "min": -30.580801755189896,
+            "max": 120.74119840562344,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.23722474297392182,
-            "min": 0.23722474297392182,
-            "max": 10.942024974262013,
-            "count": 16
+            "value": 0.03655710283524121,
+            "min": 0.035173095800641214,
+            "max": 14.265692923218012,
+            "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 7.591191775165498,
-            "min": 7.591191775165498,
-            "max": 186.01442456245422,
-            "count": 16
+            "value": 2.668668506972608,
+            "min": 2.668668506972608,
+            "max": 228.2510867714882,
+            "count": 33
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 33
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1660495718",
+        "start_time_seconds": "1660498573",
         "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training_2 --no-graphics",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1660496796"
+        "end_time_seconds": "1660500947"
     },
-    "total": 1077.3808963239999,
+    "total": 2374.062004409,
     "count": 1,
-    "self": 0.5849955929998032,
+    "self": 0.5258848069997839,
     "children": {
         "run_training.setup": {
-            "total": 0.045422839000025306,
+            "total": 0.052776323999751185,
             "count": 1,
-            "self": 0.045422839000025306
+            "self": 0.052776323999751185
         },
         "TrainerController.start_learning": {
-            "total": 1076.750477892,
+            "total": 2373.4833432780006,
             "count": 1,
-            "self": 0.8704222589813071,
+            "self": 1.9060062971307161,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.453357380000057,
+                    "total": 7.253254075999848,
                     "count": 1,
-                    "self": 10.453357380000057
+                    "self": 7.253254075999848
                 },
                 "TrainerController.advance": {
-                    "total": 1065.3259633640187,
-                    "count": 31483,
-                    "self": 0.9101491740116217,
+                    "total": 2364.221449186869,
+                    "count": 63642,
+                    "self": 1.9690848018180986,
                     "children": {
                         "env_step": {
-                            "total": 676.3301160650037,
-                            "count": 31483,
-                            "self": 613.3853840809991,
+                            "total": 1589.377502479963,
+                            "count": 63642,
+                            "self": 1460.5936606789078,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 62.487276469006474,
-                                    "count": 31483,
-                                    "self": 2.724464295002008,
+                                    "total": 127.8190716039976,
+                                    "count": 63642,
+                                    "self": 5.593932127018434,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 59.762812174004466,
-                                            "count": 31320,
-                                            "self": 19.728655800021443,
+                                            "total": 122.22513947697917,
+                                            "count": 62556,
+                                            "self": 40.70810534705606,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 40.03415637398302,
-                                                    "count": 31320,
-                                                    "self": 40.03415637398302
+                                                    "total": 81.5170341299231,
+                                                    "count": 62556,
+                                                    "self": 81.5170341299231
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.4574555149981734,
-                                    "count": 31483,
+                                    "total": 0.9647701970575326,
+                                    "count": 63642,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1074.416256594,
-                                            "count": 31483,
+                                            "total": 2368.8433057139023,
+                                            "count": 63642,
                                             "is_parallel": true,
-                                            "self": 521.7141687980189,
+                                            "self": 1032.0840914519995,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.006045080000035341,
+                                                            "total": 0.0020990499997424195,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.004609021999954166,
+                                                            "self": 0.0008599779989708622,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014360580000811751,
+                                                                    "total": 0.0012390720007715572,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014360580000811751
+                                                                    "self": 0.0012390720007715572
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06217732300001444,
+                                                            "total": 0.05814955400001054,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005548049999788418,
+                                                            "self": 0.0005360680002013396,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005626739999797792,
+                                                                    "total": 0.0005561199996009236,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005626739999797792
+                                                                    "self": 0.0005561199996009236
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.059063289000050645,
+                                                                    "total": 0.05521103000000949,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.059063289000050645
+                                                                    "self": 0.05521103000000949
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0019965550000051735,
+                                                                    "total": 0.0018463360001987894,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005149029999529375,
+                                                                    "self": 0.0005387410005823767,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001481652000052236,
+                                                                            "total": 0.0013075949996164127,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001481652000052236
+                                                                            "self": 0.0013075949996164127
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 552.7020877959811,
-                                                    "count": 31482,
+                                                    "total": 1336.7592142619028,
+                                                    "count": 63641,
                                                     "is_parallel": true,
-                                                    "self": 15.415234653966536,
+                                                    "self": 31.118827805922592,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 13.952503467011184,
-                                                            "count": 31482,
+                                                            "total": 27.896869440982755,
+                                                            "count": 63641,
                                                             "is_parallel": true,
-                                                            "self": 13.952503467011184
+                                                            "self": 27.896869440982755
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 468.87459622200686,
-                                                            "count": 31482,
+                                                            "total": 1167.999637809944,
+                                                            "count": 63641,
                                                             "is_parallel": true,
-                                                            "self": 468.87459622200686
+                                                            "self": 1167.999637809944
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 54.45975345299655,
-                                                            "count": 31482,
+                                                            "total": 109.74387920505342,
+                                                            "count": 63641,
                                                             "is_parallel": true,
-                                                            "self": 13.876780016961675,
+                                                            "self": 28.34544530705307,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 40.58297343603488,
-                                                                    "count": 251856,
+                                                                    "total": 81.39843389800035,
+                                                                    "count": 509128,
                                                                     "is_parallel": true,
-                                                                    "self": 40.58297343603488
+                                                                    "self": 81.39843389800035
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 388.08569812500343,
-                            "count": 31483,
-                            "self": 1.3359164990207546,
+                            "total": 772.874861905088,
+                            "count": 63642,
+                            "self": 3.298124051107152,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 91.49801288698382,
-                                    "count": 31483,
-                                    "self": 91.38036461398383,
+                                    "total": 185.6208761439716,
+                                    "count": 63642,
+                                    "self": 185.3944861009718,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.11764827299998615,
-                                            "count": 1,
-                                            "self": 0.11764827299998615
+                                            "total": 0.22639004299981025,
+                                            "count": 2,
+                                            "self": 0.22639004299981025
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 295.25176873899886,
-                                    "count": 209,
-                                    "self": 117.03617135099762,
+                                    "total": 583.9558617100092,
+                                    "count": 450,
+                                    "self": 229.62817828901052,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 178.21559738800124,
-                                            "count": 11406,
-                                            "self": 178.21559738800124
+                                            "total": 354.3276834209987,
+                                            "count": 22794,
+                                            "self": 354.3276834209987
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1530000847415067e-06,
+                    "total": 1.353000698145479e-06,
                     "count": 1,
-                    "self": 1.1530000847415067e-06
+                    "self": 1.353000698145479e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.10073373599993829,
+                    "total": 0.1026323650003178,
                     "count": 1,
-                    "self": 0.0016695009999239119,
+                    "self": 0.0017438289996789536,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09906423500001438,
+                            "total": 0.10088853600063885,
                             "count": 1,
-                            "self": 0.09906423500001438
+                            "self": 0.10088853600063885
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499931,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499931.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1660496795.5165658,
+                "steps": 499954,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-499954.onnx",
+                "reward": null,
+                "creation_time": 1660499676.177821,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499931.pt"
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-499954.pt"
                 ]
             },
             {
-                "steps": 500059,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500059.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1660496795.6357098,
+                "steps": 999954,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-999954.onnx",
+                "reward": null,
+                "creation_time": 1660500946.9713645,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500059.pt"
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-999954.pt"
+                ]
+            },
+            {
+                "steps": 1000082,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-1000082.onnx",
+                "reward": null,
+                "creation_time": 1660500947.0939343,
+                "auxillary_file_paths": [
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-1000082.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500059,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.9992000460624695,
-            "creation_time": 1660496795.6357098,
+            "steps": 1000082,
+            "file_path": "results/Pyramids_Training_2/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1660500947.0939343,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500059.pt"
+                "results/Pyramids_Training_2/Pyramids/Pyramids-1000082.pt"
             ]
         }
     },