First PushBlock

PushBlock.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b6e7acd95150f3b8ca885c4f12b8ad57f294c52cdfe3ad1d1a1e526d8da295
+size 488603

PushBlock/PushBlock-1499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba31925f1bcfbfd615651d3df71df72cb374fc813b9423c2a1c4d010a9e51a66
+size 488603

PushBlock/PushBlock-1499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36daf120346c40533e351754a34bc9c835e4f364267948b79c18a737a0c60216
+size 2915908

PushBlock/PushBlock-1999999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b6e7acd95150f3b8ca885c4f12b8ad57f294c52cdfe3ad1d1a1e526d8da295
+size 488603

PushBlock/PushBlock-1999999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e72406a0cd95513151dda19c19a6431016e529a9a06f107b5e77a50eece49214
+size 2915908

PushBlock/PushBlock-2000028.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98b6e7acd95150f3b8ca885c4f12b8ad57f294c52cdfe3ad1d1a1e526d8da295
+size 488603

PushBlock/PushBlock-2000028.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2f8dc0034e12affd5f58e171a86473a4b26d89b38e007698074f7075977e3b
+size 2915908

PushBlock/PushBlock-499948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:942cbf607f4ede5bdb19e44f60fae5269bad913add90d3b98919f7772b5e24dd
+size 488603

PushBlock/PushBlock-499948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d36b49b2b047a56cf337f57c43ab8944443f441c7283754da5b463b1fac2ff
+size 2915908

PushBlock/PushBlock-999967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801fe5927109fb2696f25bdf3af7f25c5cd6b98b67f1a41a8e05f567db6e2078
+size 488603

PushBlock/PushBlock-999967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e08fc9322b97001add8ec50c937c3f81bbac9fced7acf16befa8946fe54cf128
+size 2915908

PushBlock/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db2f8dc0034e12affd5f58e171a86473a4b26d89b38e007698074f7075977e3b
+size 2915908

PushBlock/events.out.tfevents.1656924840.4f4e99c81f3d.728.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5387c7672f3a0e3e2cad95f807861a01135dc00faa40ad82e540dabd33427c
+size 1018

PushBlock/events.out.tfevents.1656924851.4f4e99c81f3d.792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dde4f4c033db289c953265589dc1029943af8671f7b5b8477cbd596252656272
+size 341842

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"PushBlock": {"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": 256, "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}}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 60000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/PushBlock/PushBlock", "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": "PushBlock 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": {"PushBlock": {"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": 256, "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}}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 2000000, "time_horizon": 64, "summary_freq": 60000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/PushBlock/PushBlock", "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": "PushBlock Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -65,7 +65,7 @@ checkpoint_settings:
   run_id: PushBlock Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/PushBlock/PushBlock_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/PushBlock/PushBlock_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55024 [Flags] 2 [Guid] 2730037197 [EditorId] 588871222 [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] 55189 [Flags] 2 [Guid] 1511285201 [EditorId] 588871222 [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/PushBlock/PushBlock_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  0.079 seconds
+- Completed reload, in  0.077 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: 0.681670 ms
+UnloadTime: 0.694842 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: [4.0 KB-8.0 KB]: 671 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 18755 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
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [128.0 KB-256.0 KB]: 672 frames
+  Peak usage frame count: [128.0 KB-256.0 KB]: 18756 frames
   Requested Block Size 1.0 MB
   Peak Block count 1
-  Peak Allocated memory 152.0 KB
+  Peak Allocated memory 152.1 KB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 6
+  Peak main deferred allocation count 10
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 672 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 18756 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 4.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 672 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18756 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.6 MB
+      Peak Allocated memory 17.7 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 0.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 671 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18755 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: [8.0 KB-16.0 KB]: 672 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 18756 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 12.9 KB
@@ -275,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 672 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18756 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 671 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 18755 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.3 MB
+      Peak Block count 1
+      Peak Allocated memory 3.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 672 frames
+      Peak usage frame count: [0-1.0 KB]: 18756 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]: 672 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18756 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]: 672 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18756 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 27.9 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 332 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1656924815819,"processId":450,"allocatedMemory":1957335,"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":3450},{"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":1656926937207,"processId":803,"allocatedMemory":1957335,"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":3450},{"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

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "PushBlock.Policy.Entropy.mean": {
-            "value": 1.8362246751785278,
-            "min": 1.8362246751785278,
-            "max": 1.8362246751785278,
-            "count": 1
+            "value": 0.33722591400146484,
+            "min": 0.33722591400146484,
+            "max": 1.8695212602615356,
+            "count": 33
         },
         "PushBlock.Policy.Entropy.sum": {
-            "value": 111407.421875,
-            "min": 111407.421875,
-            "max": 111407.421875,
-            "count": 1
+            "value": 20265.927734375,
+            "min": 20265.927734375,
+            "max": 113427.59375,
+            "count": 33
         },
         "PushBlock.Step.mean": {
-            "value": 59966.0,
-            "min": 59966.0,
-            "max": 59966.0,
-            "count": 1
+            "value": 1979990.0,
+            "min": 59960.0,
+            "max": 1979990.0,
+            "count": 33
         },
         "PushBlock.Step.sum": {
-            "value": 59966.0,
-            "min": 59966.0,
-            "max": 59966.0,
-            "count": 1
+            "value": 1979990.0,
+            "min": 59960.0,
+            "max": 1979990.0,
+            "count": 33
         },
         "PushBlock.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.039823707193136215,
-            "min": 0.039823707193136215,
-            "max": 0.039823707193136215,
-            "count": 1
+            "value": 3.8565382957458496,
+            "min": 0.07406709343194962,
+            "max": 4.076359748840332,
+            "count": 33
         },
         "PushBlock.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 37.91217041015625,
-            "min": 37.91217041015625,
-            "max": 37.91217041015625,
-            "count": 1
+            "value": 8538.3759765625,
+            "min": 71.10440826416016,
+            "max": 9905.5546875,
+            "count": 33
         },
         "PushBlock.Losses.PolicyLoss.mean": {
-            "value": 0.06704430964122698,
-            "min": 0.06704430964122698,
-            "max": 0.06704430964122698,
-            "count": 1
+            "value": 0.07065016600429135,
+            "min": 0.06565261727142757,
+            "max": 0.07092491090103673,
+            "count": 33
         },
         "PushBlock.Losses.PolicyLoss.sum": {
-            "value": 1.2738418831833127,
-            "min": 1.2738418831833127,
-            "max": 1.2738418831833127,
-            "count": 1
+            "value": 2.048854814124449,
+            "min": 1.559444420121733,
+            "max": 2.056822416130065,
+            "count": 33
         },
         "PushBlock.Losses.ValueLoss.mean": {
-            "value": 0.03694163520098852,
-            "min": 0.03694163520098852,
-            "max": 0.03694163520098852,
-            "count": 1
+            "value": 0.21901374554593417,
+            "min": 0.059389760893424265,
+            "max": 0.36179679329743186,
+            "count": 33
         },
         "PushBlock.Losses.ValueLoss.sum": {
-            "value": 0.7018910688187818,
-            "min": 0.7018910688187818,
-            "max": 0.7018910688187818,
-            "count": 1
+            "value": 6.351398620832091,
+            "min": 1.3065747396553338,
+            "max": 10.492107005625524,
+            "count": 33
         },
         "PushBlock.Policy.LearningRate.mean": {
-            "value": 0.00029475132017061316,
-            "min": 0.00029475132017061316,
-            "max": 0.00029475132017061316,
-            "count": 1
+            "value": 7.56613885729655e-06,
+            "min": 7.56613885729655e-06,
+            "max": 0.0002950413425619773,
+            "count": 33
         },
         "PushBlock.Policy.LearningRate.sum": {
-            "value": 0.00560027508324165,
-            "min": 0.00560027508324165,
-            "max": 0.00560027508324165,
-            "count": 1
+            "value": 0.00021941802686159995,
+            "min": 0.00021941802686159995,
+            "max": 0.0083061859312714,
+            "count": 33
         },
         "PushBlock.Policy.Epsilon.mean": {
-            "value": 0.1982504394736842,
-            "min": 0.1982504394736842,
-            "max": 0.1982504394736842,
-            "count": 1
+            "value": 0.10252201379310344,
+            "min": 0.10252201379310344,
+            "max": 0.19834711363636365,
+            "count": 33
         },
         "PushBlock.Policy.Epsilon.sum": {
-            "value": 3.76675835,
-            "min": 3.76675835,
-            "max": 3.76675835,
-            "count": 1
+            "value": 2.9731384,
+            "min": 2.9731384,
+            "max": 5.668728600000002,
+            "count": 33
         },
         "PushBlock.Policy.Beta.mean": {
-            "value": 0.009825218903421052,
-            "min": 0.009825218903421052,
-            "max": 0.009825218903421052,
-            "count": 1
+            "value": 0.0002619491779310344,
+            "min": 0.0002619491779310344,
+            "max": 0.009834876652272728,
+            "count": 33
         },
         "PushBlock.Policy.Beta.sum": {
-            "value": 0.18667915916499997,
-            "min": 0.18667915916499997,
-            "max": 0.18667915916499997,
-            "count": 1
+            "value": 0.007596526159999999,
+            "min": 0.007596526159999999,
+            "max": 0.27688598713999996,
+            "count": 33
         },
         "PushBlock.Environment.EpisodeLength.mean": {
-            "value": 854.95,
-            "min": 854.95,
-            "max": 854.95,
-            "count": 1
+            "value": 30.343201754385966,
+            "min": 26.751054852320674,
+            "max": 744.2549019607843,
+            "count": 33
         },
         "PushBlock.Environment.EpisodeLength.sum": {
-            "value": 34198.0,
-            "min": 34198.0,
-            "max": 34198.0,
-            "count": 1
+            "value": 55346.0,
+            "min": 37957.0,
+            "max": 71322.0,
+            "count": 33
         },
         "PushBlock.Environment.CumulativeReward.mean": {
-            "value": 0.144124960526824,
-            "min": 0.144124960526824,
-            "max": 0.144124960526824,
-            "count": 1
+            "value": 4.92248410635615,
+            "min": 1.2156862590973283,
+            "max": 4.944507263670719,
+            "count": 33
         },
         "PushBlock.Environment.CumulativeReward.sum": {
-            "value": 5.76499842107296,
-            "min": 5.76499842107296,
-            "max": 5.76499842107296,
-            "count": 1
+            "value": 8983.533494099975,
+            "min": 61.99999921396375,
+            "max": 10541.689486145973,
+            "count": 33
         },
         "PushBlock.Policy.ExtrinsicReward.mean": {
-            "value": 0.144124960526824,
-            "min": 0.144124960526824,
-            "max": 0.144124960526824,
-            "count": 1
+            "value": 4.92248410635615,
+            "min": 1.2156862590973283,
+            "max": 4.944507263670719,
+            "count": 33
         },
         "PushBlock.Policy.ExtrinsicReward.sum": {
-            "value": 5.76499842107296,
-            "min": 5.76499842107296,
-            "max": 5.76499842107296,
-            "count": 1
+            "value": 8983.533494099975,
+            "min": 61.99999921396375,
+            "max": 10541.689486145973,
+            "count": 33
         },
         "PushBlock.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1
+            "count": 33
         },
         "PushBlock.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 1
+            "count": 33
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1656924741",
+        "start_time_seconds": "1656924848",
         "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/PushBlock.yaml --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PushBlock.yaml --resume --env=./trained-envs-executables/linux/PushBlock/PushBlock --run-id=PushBlock Training --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": "1656924815"
+        "end_time_seconds": "1656926937"
     },
-    "total": 74.59077404699997,
+    "total": 2088.862127583,
     "count": 1,
-    "self": 0.3834815720000506,
+    "self": 0.38092879000032553,
     "children": {
         "run_training.setup": {
-            "total": 0.042870317999927465,
+            "total": 0.04165218200000709,
             "count": 1,
-            "self": 0.042870317999927465
+            "self": 0.04165218200000709
         },
         "TrainerController.start_learning": {
-            "total": 74.16442215699999,
+            "total": 2088.439546611,
             "count": 1,
-            "self": 0.048753984000541095,
+            "self": 2.24190991901105,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.632162429000005,
+                    "total": 6.316924286000017,
                     "count": 1,
-                    "self": 8.632162429000005
+                    "self": 6.316924286000017
                 },
                 "TrainerController.advance": {
-                    "total": 65.48297698799945,
-                    "count": 2245,
-                    "self": 0.05526459400175554,
+                    "total": 2079.820143014989,
+                    "count": 96875,
+                    "self": 2.254332793024332,
                     "children": {
                         "env_step": {
-                            "total": 37.81425027399973,
-                            "count": 2245,
-                            "self": 34.09187190299599,
+                            "total": 1235.921350959969,
+                            "count": 96875,
+                            "self": 1132.0936363799929,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 3.6983563540014757,
-                                    "count": 2245,
-                                    "self": 0.18426225000007435,
+                                    "total": 102.73826761500209,
+                                    "count": 96875,
+                                    "self": 5.526802036970594,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 3.5140941040014013,
-                                            "count": 2237,
-                                            "self": 1.091724532001649,
+                                            "total": 97.2114655780315,
+                                            "count": 62519,
+                                            "self": 31.295723613979362,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 2.4223695719997522,
-                                                    "count": 2237,
-                                                    "self": 2.4223695719997522
+                                                    "total": 65.91574196405213,
+                                                    "count": 62519,
+                                                    "self": 65.91574196405213
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.024022017002266693,
-                                    "count": 2244,
+                                    "total": 1.0894469649739449,
+                                    "count": 96875,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 74.08486261399912,
-                                            "count": 2244,
+                                            "total": 2083.917374952014,
+                                            "count": 96875,
                                             "is_parallel": true,
-                                            "self": 44.6305240420005,
+                                            "self": 1107.3758011870466,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005512229000032676,
+                                                            "total": 0.002442584000050374,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00381649600012679,
+                                                            "self": 0.000716575000069497,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0016957329999058857,
+                                                                    "total": 0.001726008999980877,
                                                                     "count": 4,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0016957329999058857
+                                                                    "self": 0.001726008999980877
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.035090766999928746,
+                                                            "total": 0.03243801899998289,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007449989998349338,
+                                                            "self": 0.0007644500000196786,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007464210000307503,
+                                                                    "total": 0.0007314270000051692,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007464210000307503
+                                                                    "self": 0.0007314270000051692
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0313733369999909,
+                                                                    "total": 0.028701266999973996,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0313733369999909
+                                                                    "self": 0.028701266999973996
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002226010000072165,
+                                                                    "total": 0.002240874999984044,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043967600004179985,
+                                                                    "self": 0.0004186319999917032,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0017863340000303651,
+                                                                            "total": 0.0018222429999923406,
                                                                             "count": 4,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0017863340000303651
+                                                                            "self": 0.0018222429999923406
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 29.45433857199862,
-                                                    "count": 2243,
+                                                    "total": 976.5415737649676,
+                                                    "count": 96874,
                                                     "is_parallel": true,
-                                                    "self": 1.4206518659983658,
+                                                    "self": 47.16540336711739,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.466212650000216,
-                                                            "count": 2243,
+                                                            "total": 42.528755005947914,
+                                                            "count": 96874,
                                                             "is_parallel": true,
-                                                            "self": 1.466212650000216
+                                                            "self": 42.528755005947914
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 22.032857154000453,
-                                                            "count": 2243,
+                                                            "total": 744.8899298919922,
+                                                            "count": 96874,
                                                             "is_parallel": true,
-                                                            "self": 22.032857154000453
+                                                            "self": 744.8899298919922
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 4.534616901999584,
-                                                            "count": 2243,
+                                                            "total": 141.95748549991004,
+                                                            "count": 96874,
                                                             "is_parallel": true,
-                                                            "self": 0.8396178719958698,
+                                                            "self": 30.022575108893875,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 3.6949990300037143,
-                                                                    "count": 8972,
+                                                                    "total": 111.93491039101616,
+                                                                    "count": 387496,
                                                                     "is_parallel": true,
-                                                                    "self": 3.6949990300037143
+                                                                    "self": 111.93491039101616
                                                                 }
                                                             }
                                                         }
@@ -314,24 +314,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 27.613462119997962,
-                            "count": 2244,
-                            "self": 0.06752446899633924,
+                            "total": 841.6444592619955,
+                            "count": 96875,
+                            "self": 3.980088374927732,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 6.781744252001886,
-                                    "count": 2244,
-                                    "self": 6.781744252001886
+                                    "total": 249.56262402706557,
+                                    "count": 96875,
+                                    "self": 249.29092566906593,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.2716983579996395,
+                                            "count": 4,
+                                            "self": 0.2716983579996395
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 20.764193398999737,
-                                    "count": 24,
-                                    "self": 11.137951236002436,
+                                    "total": 588.1017468600022,
+                                    "count": 957,
+                                    "self": 309.67303375698,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 9.6262421629973,
-                                            "count": 1623,
-                                            "self": 9.6262421629973
+                                            "total": 278.42871310302223,
+                                            "count": 46263,
+                                            "self": 278.42871310302223
                                         }
                                     }
                                 }
@@ -340,19 +347,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.7050000451490632e-06,
+                    "total": 1.021000116452342e-06,
                     "count": 1,
-                    "self": 1.7050000451490632e-06
+                    "self": 1.021000116452342e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0005270509999490969,
+                    "total": 0.06056837000005544,
                     "count": 1,
-                    "self": 2.5002999905154866e-05,
+                    "self": 0.0008598590002293349,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.000502048000043942,
+                            "total": 0.0597085109998261,
                             "count": 1,
-                            "self": 0.000502048000043942
+                            "self": 0.0597085109998261
                         }
                     }
                 }

run_logs/training_status.json

@@ -3,5 +3,63 @@
         "stats_format_version": "0.3.0",
         "mlagents_version": "0.29.0.dev0",
         "torch_version": "1.8.1+cu102"
+    },
+    "PushBlock": {
+        "checkpoints": [
+            {
+                "steps": 499948,
+                "file_path": "results/PushBlock Training/PushBlock/PushBlock-499948.onnx",
+                "reward": 4.62898857029421,
+                "creation_time": 1656925348.537285,
+                "auxillary_file_paths": [
+                    "results/PushBlock Training/PushBlock/PushBlock-499948.pt"
+                ]
+            },
+            {
+                "steps": 999967,
+                "file_path": "results/PushBlock Training/PushBlock/PushBlock-999967.onnx",
+                "reward": 4.975780539759776,
+                "creation_time": 1656925870.441136,
+                "auxillary_file_paths": [
+                    "results/PushBlock Training/PushBlock/PushBlock-999967.pt"
+                ]
+            },
+            {
+                "steps": 1499995,
+                "file_path": "results/PushBlock Training/PushBlock/PushBlock-1499995.onnx",
+                "reward": 4.835842597119986,
+                "creation_time": 1656926400.9487886,
+                "auxillary_file_paths": [
+                    "results/PushBlock Training/PushBlock/PushBlock-1499995.pt"
+                ]
+            },
+            {
+                "steps": 1999999,
+                "file_path": "results/PushBlock Training/PushBlock/PushBlock-1999999.onnx",
+                "reward": 4.98148250579834,
+                "creation_time": 1656926936.7831054,
+                "auxillary_file_paths": [
+                    "results/PushBlock Training/PushBlock/PushBlock-1999999.pt"
+                ]
+            },
+            {
+                "steps": 2000028,
+                "file_path": "results/PushBlock Training/PushBlock/PushBlock-2000028.onnx",
+                "reward": 4.981947522414358,
+                "creation_time": 1656926936.847142,
+                "auxillary_file_paths": [
+                    "results/PushBlock Training/PushBlock/PushBlock-2000028.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000028,
+            "file_path": "results/PushBlock Training/PushBlock.onnx",
+            "reward": 4.981947522414358,
+            "creation_time": 1656926936.847142,
+            "auxillary_file_paths": [
+                "results/PushBlock Training/PushBlock/PushBlock-2000028.pt"
+            ]
+        }
     }
 }