First try

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840f24e70fe476f9f8bc09d71bb7fb8a37b1135026191e38d47063676ae466bd
+oid sha256:6838d992cda453366d595469efa9d16134ea76d2eb9a2da6dde85822ad1641f3
 size 1417437

Pyramids/Pyramids-1499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b999c79439468febc24b29adb23ce1703958c121be371a8aba03420778c5b5c
+size 1417437

Pyramids/Pyramids-1499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5839f9b33785376896a270a290f0cd25b13fa69b998be351b46b41c8eb92d2f2
+size 8652382

Pyramids/Pyramids-1999962.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd4001ad438022dbddc942aa094f2047800b6871faceb50b19d8269f44f77b5
+size 1417437

Pyramids/Pyramids-1999962.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8972095fa326762811568ad2173d7ef231747b5781428df4a32851a64f6e46c
+size 8652382

Pyramids/Pyramids-2499907.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609a2af16bceb704884acf237fb911114eb1de0d46b4cc204d794b1464e7b9b8
+size 1417437

Pyramids/Pyramids-2499907.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b73a4a324a2bb0dc38ccb6fa4c032fae264d77285fc6c4119ddc612445ec6e7
+size 8652382

Pyramids/Pyramids-2999981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6838d992cda453366d595469efa9d16134ea76d2eb9a2da6dde85822ad1641f3
+size 1417437

Pyramids/Pyramids-2999981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4c4819249961b507f4281970523246bc1fcb42fc2fa727334d1c8010bc7f90
+size 8652446

Pyramids/Pyramids-3000109.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6838d992cda453366d595469efa9d16134ea76d2eb9a2da6dde85822ad1641f3
+size 1417437

Pyramids/Pyramids-3000109.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da1d0063f196c48b012b6d8927bdf6eb4def0b453c5a3aa1c404bdee31829a5
+size 8652446

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:137269d19bb2c10489f024ce00437aaaccbae904629fed801f1cf8a6256f2bdc
-size 8652382
+oid sha256:1da1d0063f196c48b012b6d8927bdf6eb4def0b453c5a3aa1c404bdee31829a5
+size 8652446

Pyramids/{events.out.tfevents.1673436704.f243fdf62f0f.19935.0 → events.out.tfevents.1673436841.f243fdf62f0f.21033.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d866b7cbefc38ab224f58d85ac3191e2955982c882671349be7f6732db9d40d
-size 1326
+oid sha256:8de38b1466b6ede8c4a410ab4d768ab105de4d5164bc8f442f721a9d15e38a8b
+size 961857

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": 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}
+{"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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -79,7 +79,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 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]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55147 [Flags] 2 [Guid] 2492498485 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +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  0.081 seconds
+- Completed reload, in  0.096 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)
@@ -65,30 +65,15 @@ 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: 0.698945 ms
+UnloadTime: 0.844777 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]: 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
+      Peak usage frame count: [16.0 KB-32.0 KB]: 8142 frames, [32.0 KB-64.0 KB]: 33233 frames, [64.0 KB-128.0 KB]: 14893 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
@@ -143,12 +128,12 @@ 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 7]
       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 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -198,12 +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
@@ -219,25 +204,25 @@ 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]: 151 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 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 12508
+  Peak main deferred allocation count 12451
     [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]: 449 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56268 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 26.3 MB
+      Peak Block count 3
+      Peak Allocated memory 30.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 450 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 23.4 MB
@@ -269,13 +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]: 449 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56268 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]: 450 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56269 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -287,13 +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]: 151 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55970 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]: 449 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56268 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
@@ -305,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 450 frames
+      Peak usage frame count: [0-1.0 KB]: 56269 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]: 450 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56269 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]: 450 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 56269 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 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":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}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673443429577,"processId":21054,"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

@@ -1,75 +1,257 @@
 {
     "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.1401660442352295,
+            "min": 0.12643176317214966,
+            "max": 1.4079315662384033,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4198.25341796875,
+            "min": 3822.775634765625,
+            "max": 42711.01171875,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999981.0,
+            "min": 29927.0,
+            "max": 2999981.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999981.0,
+            "min": 29927.0,
+            "max": 2999981.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8043355941772461,
+            "min": -0.12856468558311462,
+            "max": 0.8474668264389038,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 238.08334350585938,
+            "min": -31.112653732299805,
+            "max": 252.5451202392578,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.006953133270144463,
+            "min": -0.02320166304707527,
+            "max": 0.3179396986961365,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -2.0581274032592773,
+            "min": -6.357255458831787,
+            "max": 76.62346649169922,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06712611117325228,
+            "min": 0.06561516648982144,
+            "max": 0.07333423835752044,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9397655564255318,
+            "min": 0.4967884381028059,
+            "max": 1.080696525731279,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.016006519057473603,
+            "min": 0.0007565912627410983,
+            "max": 0.01634440915742224,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22409126680463046,
+            "min": 0.009835686415634278,
+            "max": 0.233348077206756,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.5028709276476204e-06,
+            "min": 1.5028709276476204e-06,
+            "max": 0.0002984113291009857,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.1040192987066684e-05,
+            "min": 2.1040192987066684e-05,
+            "max": 0.004010810263063266,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10050092380952383,
+            "min": 0.10050092380952383,
+            "max": 0.19947044285714285,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4070129333333337,
+            "min": 1.3962931,
+            "max": 2.7369367333333336,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.0042288571428606e-05,
+            "min": 6.0042288571428606e-05,
+            "max": 0.00994709724142857,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008405920400000005,
+            "min": 0.0008405920400000005,
+            "max": 0.13369997966000002,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.005792219191789627,
+            "min": 0.005737673491239548,
+            "max": 0.5316672921180725,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.08109106868505478,
+            "min": 0.08032742887735367,
+            "max": 3.7216711044311523,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 229.5581395348837,
+            "min": 217.8030303030303,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29613.0,
+            "min": 16598.0,
+            "max": 33071.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7550093586323783,
+            "min": -0.9999375520274043,
+            "max": 1.7829774280911999,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 224.64119790494442,
+            "min": -31.998001664876938,
+            "max": 240.10419809818268,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7550093586323783,
+            "min": -0.9999375520274043,
+            "max": 1.7829774280911999,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 224.64119790494442,
+            "min": -31.998001664876938,
+            "max": 240.10419809818268,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.014175047012713549,
+            "min": 0.014006038754007733,
+            "max": 9.618010953945273,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.8144060176273342,
+            "min": 1.80437104270095,
+            "max": 163.50618621706963,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673436701",
+        "start_time_seconds": "1673436838",
         "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --force --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": "1673436748"
+        "end_time_seconds": "1673443429"
     },
-    "total": 46.46965647600064,
+    "total": 6590.957671723,
     "count": 1,
-    "self": 0.26641510800072865,
+    "self": 0.3866753090014754,
     "children": {
         "run_training.setup": {
-            "total": 0.10572795200005203,
+            "total": 0.10608782399958727,
             "count": 1,
-            "self": 0.10572795200005203
+            "self": 0.10608782399958727
         },
         "TrainerController.start_learning": {
-            "total": 46.097513415999856,
+            "total": 6590.464908589999,
             "count": 1,
-            "self": 0.026605913003550086,
+            "self": 3.5416784518001805,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.195178996999857,
+                    "total": 6.270754094999575,
                     "count": 1,
-                    "self": 6.195178996999857
+                    "self": 6.270754094999575
                 },
                 "TrainerController.advance": {
-                    "total": 39.70947748799699,
-                    "count": 1501,
-                    "self": 0.028000660046927806,
+                    "total": 6580.564439250199,
+                    "count": 194589,
+                    "self": 3.7435202929864317,
                     "children": {
                         "env_step": {
-                            "total": 25.202466002982874,
-                            "count": 1501,
-                            "self": 22.78025580297981,
+                            "total": 4615.4374576440505,
+                            "count": 194589,
+                            "self": 4311.92120395386,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 2.4054239740135017,
-                                    "count": 1501,
-                                    "self": 0.10194748901540152,
+                                    "total": 301.2621689608759,
+                                    "count": 194589,
+                                    "self": 12.609598710701903,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 2.3034764849981,
-                                            "count": 1500,
-                                            "self": 0.7823975809851618,
+                                            "total": 288.652570250174,
+                                            "count": 187563,
+                                            "self": 98.22204072685145,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 1.5210789040129384,
-                                                    "count": 1500,
-                                                    "self": 1.5210789040129384
+                                                    "total": 190.43052952332255,
+                                                    "count": 187563,
+                                                    "self": 190.43052952332255
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.01678622598956281,
-                                    "count": 1500,
+                                    "total": 2.2540847293148545,
+                                    "count": 194589,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 45.92071685199244,
-                                            "count": 1500,
+                                            "total": 6578.318900204209,
+                                            "count": 194589,
                                             "is_parallel": true,
-                                            "self": 25.479420575011318,
+                                            "self": 2561.6276519349885,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -78,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0017562080001880531,
+                                                            "total": 0.0018145660005757236,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006479540006694151,
+                                                            "self": 0.0007151890004024608,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001108253999518638,
+                                                                    "total": 0.0010993770001732628,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001108253999518638
+                                                                    "self": 0.0010993770001732628
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04900581600031728,
+                                                            "total": 0.04712240299977566,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0004843380002057529,
+                                                            "self": 0.0004951319997417158,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000555407000319974,
+                                                                    "total": 0.00046936400030972436,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000555407000319974
+                                                                    "self": 0.00046936400030972436
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.046291620999909355,
+                                                                    "total": 0.04454450600042037,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.046291620999909355
+                                                                    "self": 0.04454450600042037
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016744499998821993,
+                                                                    "total": 0.001613400999303849,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041906700062099844,
+                                                                    "self": 0.0004167139995843172,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001255382999261201,
+                                                                            "total": 0.0011966869997195317,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001255382999261201
+                                                                            "self": 0.0011966869997195317
                                                                         }
                                                                     }
                                                                 }
@@ -128,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 20.44129627698112,
-                                                    "count": 1499,
+                                                    "total": 4016.6912482692205,
+                                                    "count": 194588,
                                                     "is_parallel": true,
-                                                    "self": 0.6670674049782974,
+                                                    "self": 82.73168055696078,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.5629458650037122,
-                                                            "count": 1499,
+                                                            "total": 69.23609923110143,
+                                                            "count": 194588,
                                                             "is_parallel": true,
-                                                            "self": 0.5629458650037122
+                                                            "self": 69.23609923110143
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 16.923522237988436,
-                                                            "count": 1499,
+                                                            "total": 3580.09317806993,
+                                                            "count": 194588,
                                                             "is_parallel": true,
-                                                            "self": 16.923522237988436
+                                                            "self": 3580.09317806993
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 2.2877607690106743,
-                                                            "count": 1499,
+                                                            "total": 284.6302904112281,
+                                                            "count": 194588,
                                                             "is_parallel": true,
-                                                            "self": 0.5250153039423822,
+                                                            "self": 67.44226652618272,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.762745465068292,
-                                                                    "count": 11992,
+                                                                    "total": 217.18802388504537,
+                                                                    "count": 1556704,
                                                                     "is_parallel": true,
-                                                                    "self": 1.762745465068292
+                                                                    "self": 217.18802388504537
                                                                 }
                                                             }
                                                         }
@@ -168,24 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 14.47901082496719,
-                            "count": 1500,
-                            "self": 0.03075918296326563,
+                            "total": 1961.3834613131621,
+                            "count": 194589,
+                            "self": 7.157003252955292,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 3.128990376002548,
-                                    "count": 1500,
-                                    "self": 3.128990376002548
+                                    "total": 452.3808608881827,
+                                    "count": 194589,
+                                    "self": 451.82043653918026,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5604243490024601,
+                                            "count": 6,
+                                            "self": 0.5604243490024601
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 11.319261266001376,
-                                    "count": 6,
-                                    "self": 4.27235093600666,
+                                    "total": 1501.845597172024,
+                                    "count": 1400,
+                                    "self": 582.7536340652014,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 7.0469103299947164,
-                                            "count": 519,
-                                            "self": 7.0469103299947164
+                                            "total": 919.0919631068227,
+                                            "count": 68412,
+                                            "self": 919.0919631068227
                                         }
                                     }
                                 }
@@ -194,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3720000424655154e-06,
+                    "total": 1.0139992809854448e-06,
                     "count": 1,
-                    "self": 1.3720000424655154e-06
+                    "self": 1.0139992809854448e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1662496459994145,
+                    "total": 0.08803577900107484,
                     "count": 1,
-                    "self": 0.0017524629993204144,
+                    "self": 0.0017486100005044136,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.16449718300009408,
+                            "total": 0.08628716900057043,
                             "count": 1,
-                            "self": 0.16449718300009408
+                            "self": 0.08628716900057043
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 22242,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-22242.onnx",
-                "reward": null,
-                "creation_time": 1673436747.8518755,
+                "steps": 1499969,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499969.onnx",
+                "reward": 1.7134999930858612,
+                "creation_time": 1673439967.4689264,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-22242.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499969.pt"
+                ]
+            },
+            {
+                "steps": 1999962,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999962.onnx",
+                "reward": 1.8176666647195816,
+                "creation_time": 1673441106.8872263,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999962.pt"
+                ]
+            },
+            {
+                "steps": 2499907,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499907.onnx",
+                "reward": 1.7802856862545013,
+                "creation_time": 1673442276.0324674,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499907.pt"
+                ]
+            },
+            {
+                "steps": 2999981,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999981.onnx",
+                "reward": 1.8649999871850014,
+                "creation_time": 1673443429.113468,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999981.pt"
+                ]
+            },
+            {
+                "steps": 3000109,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000109.onnx",
+                "reward": 1.8516666574610605,
+                "creation_time": 1673443429.2151537,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000109.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 22242,
+            "steps": 3000109,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1673436747.8518755,
+            "reward": 1.8516666574610605,
+            "creation_time": 1673443429.2151537,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-22242.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000109.pt"
             ]
         }
     },