First try

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dff653c82101830faa8251c595e01468667f0754432c33ae6dbef4070cbf2be
+oid sha256:840f24e70fe476f9f8bc09d71bb7fb8a37b1135026191e38d47063676ae466bd
 size 1417437

Pyramids/Pyramids-1000129.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0a89230860729c0c1736dcc0111285e1e03cbcbfe31611dd2ba81f4b74d53e08
-size 8652382

Pyramids/{Pyramids-1000129.onnx → Pyramids-22242.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dff653c82101830faa8251c595e01468667f0754432c33ae6dbef4070cbf2be
+oid sha256:840f24e70fe476f9f8bc09d71bb7fb8a37b1135026191e38d47063676ae466bd
 size 1417437

Pyramids/{Pyramids-999873.pt → Pyramids-22242.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8ab7a5cbe2802354064d291a73e7789003707b2215417baa513f4a5b3a4b17
+oid sha256:137269d19bb2c10489f024ce00437aaaccbae904629fed801f1cf8a6256f2bdc
 size 8652382

Pyramids/Pyramids-499900.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8a634e71afe3d19175698bb3a7d529f141e324304834ad64052293a9acfecfa8
-size 1417437

Pyramids/Pyramids-499900.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b37c572b4b368e133340062c7abb3adc228a4c241e4699c5b909aad37689a18
-size 8652382

Pyramids/Pyramids-999873.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5dff653c82101830faa8251c595e01468667f0754432c33ae6dbef4070cbf2be
-size 1417437

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a89230860729c0c1736dcc0111285e1e03cbcbfe31611dd2ba81f4b74d53e08
+oid sha256:137269d19bb2c10489f024ce00437aaaccbae904629fed801f1cf8a6256f2bdc
 size 8652382

Pyramids/{events.out.tfevents.1673433658.f243fdf62f0f.6964.0 → events.out.tfevents.1673436704.f243fdf62f0f.19935.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71f90bb62953cde2d01a1a4106c698f9b16c5df5e0b2d4c640cbced949c282a3
-size 332962
+oid sha256:4d866b7cbefc38ab224f58d85ac3191e2955982c882671349be7f6732db9d40d
+size 1326

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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": 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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": 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: 1000000
+    max_steps: 3000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,14 +1,11 @@
-Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
-Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55077 [Flags] 2 [Guid] 894748789 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55285 [Flags] 2 [Guid] 3091258855 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [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/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+[Subsystems] Discovering subsystems at path /content/ml-agents/ml-agents/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 NullGfxDevice:
@@ -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  0.088 seconds
+- Completed reload, in  0.081 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)
@@ -68,15 +65,30 @@ 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: 0.803517 ms
+UnloadTime: 0.698945 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
+UnityEngine.StackTraceUtility:ExtractStackTrace () (at /home/bokken/buildslave/unity/build/Runtime/Export/Scripting/StackTrace.cs:37)
+UnityEngine.DebugLogHandler:LogFormat (UnityEngine.LogType,UnityEngine.Object,string,object[])
+UnityEngine.Logger:Log (UnityEngine.LogType,object)
+UnityEngine.Debug:Log (object)
+Unity.MLAgents.RpcCommunicator:Exchange (Unity.MLAgents.CommunicatorObjects.UnityOutputProto) (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs:497)
+Unity.MLAgents.RpcCommunicator:SendBatchedMessageHelper () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs:393)
+Unity.MLAgents.RpcCommunicator:DecideBatch () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs:320)
+Unity.MLAgents.Policies.RemotePolicy:DecideAction () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Policies/RemotePolicy.cs:67)
+Unity.MLAgents.Agent:DecideAction () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Agent.cs:1373)
+Unity.MLAgents.Academy:EnvironmentStep () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Academy.cs:586)
+Unity.MLAgents.AcademyFixedUpdateStepper:FixedUpdate () (at /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Academy.cs:43)
+
+(Filename: /home/singularity/Downloads/ml-agents-main/com.unity.ml-agents/Runtime/Communicator/RpcCommunicator.cs Line: 497)
+
 Setting up 1 worker threads for Enlighten.
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4193 frames, [32.0 KB-64.0 KB]: 12266 frames, [64.0 KB-128.0 KB]: 2310 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 204 frames, [32.0 KB-64.0 KB]: 236 frames, [64.0 KB-128.0 KB]: 9 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
@@ -131,12 +143,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       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 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -144,7 +156,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 320.0 KB
-      Peak Allocated Bytes 251.5 KB
+      Peak Allocated Bytes 251.6 KB
       Overflow Count 4
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
@@ -186,12 +198,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       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
       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
@@ -207,28 +219,28 @@ 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]: 18471 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 151 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 11954
+  Peak main deferred allocation count 12508
     [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]: 18769 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 449 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.6 MB
+      Peak Block count 2
+      Peak Allocated memory 26.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 450 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.2 MB
+      Peak Allocated memory 23.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +269,13 @@ 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]: 18769 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 449 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]: 18770 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 450 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +287,13 @@ 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]: 18471 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 151 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]: 18769 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 449 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
@@ -293,25 +305,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18770 frames
+      Peak usage frame count: [0-1.0 KB]: 450 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]: 18770 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 450 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]: 18770 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 450 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673435685502,"processId":6985,"allocatedMemory":1957332,"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":3447},{"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":1673436748071,"processId":19956,"allocatedMemory":1957392,"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":3507},{"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

@@ -1,190 +1,8 @@
 {
     "name": "root",
-    "gauges": {
-        "Pyramids.Policy.Entropy.mean": {
-            "value": 0.4685787558555603,
-            "min": 0.4685787558555603,
-            "max": 1.4757680892944336,
-            "count": 33
-        },
-        "Pyramids.Policy.Entropy.sum": {
-            "value": 14109.84375,
-            "min": 14109.84375,
-            "max": 44768.90234375,
-            "count": 33
-        },
-        "Pyramids.Step.mean": {
-            "value": 989873.0,
-            "min": 29931.0,
-            "max": 989873.0,
-            "count": 33
-        },
-        "Pyramids.Step.sum": {
-            "value": 989873.0,
-            "min": 29931.0,
-            "max": 989873.0,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.07984339445829391,
-            "min": -0.1728469878435135,
-            "max": 0.3723273277282715,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -19.16241455078125,
-            "min": -40.96473693847656,
-            "max": 98.66674041748047,
-            "count": 33
-        },
-        "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.20975856482982635,
-            "min": -2.072092294692993,
-            "max": 0.7074848413467407,
-            "count": 33
-        },
-        "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -50.34205627441406,
-            "min": -522.167236328125,
-            "max": 187.48348999023438,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07220396597815726,
-            "min": 0.06525297152824998,
-            "max": 0.07479138664777195,
-            "count": 33
-        },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0108555236942016,
-            "min": 0.5235397065344036,
-            "max": 1.0508153965929525,
-            "count": 33
-        },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.19289495998710673,
-            "min": 0.0006608483714470843,
-            "max": 1.3755555756390092,
-            "count": 33
-        },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 2.700529439819494,
-            "min": 0.00925187720025918,
-            "max": 20.63333363458514,
-            "count": 33
-        },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.194011887742857e-06,
-            "min": 7.194011887742857e-06,
-            "max": 0.00029523381587444287,
-            "count": 33
-        },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0001007161664284,
-            "min": 0.0001007161664284,
-            "max": 0.0037580896473035003,
-            "count": 33
-        },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10239797142857145,
-            "min": 0.10239797142857145,
-            "max": 0.19841127142857143,
-            "count": 33
-        },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4335716000000003,
-            "min": 1.3888789,
-            "max": 2.6526965,
-            "count": 33
-        },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002495573457142858,
-            "min": 0.0002495573457142858,
-            "max": 0.009841286015714285,
-            "count": 33
-        },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.003493802840000001,
-            "min": 0.003493802840000001,
-            "max": 0.12528438035,
-            "count": 33
-        },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.009107543155550957,
-            "min": 0.009107543155550957,
-            "max": 0.40546226501464844,
-            "count": 33
-        },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1275056004524231,
-            "min": 0.1275056004524231,
-            "max": 2.838235855102539,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 978.9333333333333,
-            "min": 482.359375,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29368.0,
-            "min": 16730.0,
-            "max": 33065.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.7794333825508754,
-            "min": -0.999962551984936,
-            "max": 1.3623898021750531,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -23.38300147652626,
-            "min": -31.998801663517952,
-            "max": 83.12579830735922,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.7794333825508754,
-            "min": -0.999962551984936,
-            "max": 1.3623898021750531,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -23.38300147652626,
-            "min": -31.998801663517952,
-            "max": 83.12579830735922,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.09779099830581496,
-            "min": 0.06319771810958627,
-            "max": 8.053644975318628,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.933729949174449,
-            "min": 2.933729949174449,
-            "max": 136.91196458041668,
-            "count": 33
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 33
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 33
-        }
-    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673433655",
+        "start_time_seconds": "1673436701",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "mlagents_version": "0.29.0.dev0",
@@ -192,66 +10,66 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673435685"
+        "end_time_seconds": "1673436748"
     },
-    "total": 2030.024422533,
+    "total": 46.46965647600064,
     "count": 1,
-    "self": 0.4376969850000023,
+    "self": 0.26641510800072865,
     "children": {
         "run_training.setup": {
-            "total": 0.10891131199991833,
+            "total": 0.10572795200005203,
             "count": 1,
-            "self": 0.10891131199991833
+            "self": 0.10572795200005203
         },
         "TrainerController.start_learning": {
-            "total": 2029.477814236,
+            "total": 46.097513415999856,
             "count": 1,
-            "self": 1.330467363979551,
+            "self": 0.026605913003550086,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.2831109459998515,
+                    "total": 6.195178996999857,
                     "count": 1,
-                    "self": 6.2831109459998515
+                    "self": 6.195178996999857
                 },
                 "TrainerController.advance": {
-                    "total": 2021.7393277810206,
-                    "count": 63506,
-                    "self": 1.316507256105524,
+                    "total": 39.70947748799699,
+                    "count": 1501,
+                    "self": 0.028000660046927806,
                     "children": {
                         "env_step": {
-                            "total": 1369.3422801499553,
-                            "count": 63506,
-                            "self": 1263.5656444809617,
+                            "total": 25.202466002982874,
+                            "count": 1501,
+                            "self": 22.78025580297981,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 104.99076349399274,
-                                    "count": 63506,
-                                    "self": 4.301765443938848,
+                                    "total": 2.4054239740135017,
+                                    "count": 1501,
+                                    "self": 0.10194748901540152,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 100.6889980500539,
-                                            "count": 62565,
-                                            "self": 33.9186716610518,
+                                            "total": 2.3034764849981,
+                                            "count": 1500,
+                                            "self": 0.7823975809851618,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 66.7703263890021,
-                                                    "count": 62565,
-                                                    "self": 66.7703263890021
+                                                    "total": 1.5210789040129384,
+                                                    "count": 1500,
+                                                    "self": 1.5210789040129384
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7858721750008044,
-                                    "count": 63506,
+                                    "total": 0.01678622598956281,
+                                    "count": 1500,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2025.1175958369731,
-                                            "count": 63506,
+                                            "total": 45.92071685199244,
+                                            "count": 1500,
                                             "is_parallel": true,
-                                            "self": 862.6698818980201,
+                                            "self": 25.479420575011318,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +78,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017815759999848524,
+                                                            "total": 0.0017562080001880531,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006515790003049915,
+                                                            "self": 0.0006479540006694151,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001129996999679861,
+                                                                    "total": 0.001108253999518638,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001129996999679861
+                                                                    "self": 0.001108253999518638
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.050063350000073115,
+                                                            "total": 0.04900581600031728,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005749709998781327,
+                                                            "self": 0.0004843380002057529,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004970970001068054,
+                                                                    "total": 0.000555407000319974,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004970970001068054
+                                                                    "self": 0.000555407000319974
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04724182300014945,
+                                                                    "total": 0.046291620999909355,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04724182300014945
+                                                                    "self": 0.046291620999909355
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017494589999387244,
+                                                                    "total": 0.0016744499998821993,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042636499961190566,
+                                                                    "self": 0.00041906700062099844,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013230940003268188,
+                                                                            "total": 0.001255382999261201,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013230940003268188
+                                                                            "self": 0.001255382999261201
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +128,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1162.447713938953,
-                                                    "count": 63505,
+                                                    "total": 20.44129627698112,
+                                                    "count": 1499,
                                                     "is_parallel": true,
-                                                    "self": 27.853273335965923,
+                                                    "self": 0.6670674049782974,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.174678673012295,
-                                                            "count": 63505,
+                                                            "total": 0.5629458650037122,
+                                                            "count": 1499,
                                                             "is_parallel": true,
-                                                            "self": 23.174678673012295
+                                                            "self": 0.5629458650037122
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1015.9427356120254,
-                                                            "count": 63505,
+                                                            "total": 16.923522237988436,
+                                                            "count": 1499,
                                                             "is_parallel": true,
-                                                            "self": 1015.9427356120254
+                                                            "self": 16.923522237988436
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 95.47702631794937,
-                                                            "count": 63505,
+                                                            "total": 2.2877607690106743,
+                                                            "count": 1499,
                                                             "is_parallel": true,
-                                                            "self": 22.479759496958195,
+                                                            "self": 0.5250153039423822,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 72.99726682099117,
-                                                                    "count": 508040,
+                                                                    "total": 1.762745465068292,
+                                                                    "count": 11992,
                                                                     "is_parallel": true,
-                                                                    "self": 72.99726682099117
+                                                                    "self": 1.762745465068292
                                                                 }
                                                             }
                                                         }
@@ -350,31 +168,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 651.0805403749598,
-                            "count": 63506,
-                            "self": 2.4331199810271755,
+                            "total": 14.47901082496719,
+                            "count": 1500,
+                            "self": 0.03075918296326563,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 148.31782828892847,
-                                    "count": 63506,
-                                    "self": 148.0747111019282,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.24311718700027996,
-                                            "count": 2,
-                                            "self": 0.24311718700027996
-                                        }
-                                    }
+                                    "total": 3.128990376002548,
+                                    "count": 1500,
+                                    "self": 3.128990376002548
                                 },
                                 "_update_policy": {
-                                    "total": 500.32959210500417,
-                                    "count": 455,
-                                    "self": 192.48118916199337,
+                                    "total": 11.319261266001376,
+                                    "count": 6,
+                                    "self": 4.27235093600666,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 307.8484029430108,
-                                            "count": 22743,
-                                            "self": 307.8484029430108
+                                            "total": 7.0469103299947164,
+                                            "count": 519,
+                                            "self": 7.0469103299947164
                                         }
                                     }
                                 }
@@ -383,19 +194,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.6110002434288617e-06,
+                    "total": 1.3720000424655154e-06,
                     "count": 1,
-                    "self": 1.6110002434288617e-06
+                    "self": 1.3720000424655154e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12490653399981966,
+                    "total": 0.1662496459994145,
                     "count": 1,
-                    "self": 0.0016855049998412142,
+                    "self": 0.0017524629993204144,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12322102899997844,
+                            "total": 0.16449718300009408,
                             "count": 1,
-                            "self": 0.12322102899997844
+                            "self": 0.16449718300009408
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,22 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499900,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499900.onnx",
-                "reward": 1.5860000103712082,
-                "creation_time": 1673434638.0416305,
+                "steps": 22242,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-22242.onnx",
+                "reward": null,
+                "creation_time": 1673436747.8518755,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499900.pt"
-                ]
-            },
-            {
-                "steps": 999873,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999873.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1673435684.9392204,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999873.pt"
-                ]
-            },
-            {
-                "steps": 1000129,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000129.onnx",
-                "reward": -0.999800056219101,
-                "creation_time": 1673435685.1176193,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000129.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-22242.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000129,
+            "steps": 22242,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.999800056219101,
-            "creation_time": 1673435685.1176193,
+            "reward": null,
+            "creation_time": 1673436747.8518755,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000129.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-22242.pt"
             ]
         }
     },