Second Version

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e0064b18f053e006c3d373c64ff6d5701585350e3104fb4cddbb20da9ac855
+oid sha256:c187d97ca2c574c1b1c52c7395958ce97c89fabe1563f324fd030eda5dcad2f5
 size 1418184

Pyramids/{Pyramids-1028863.onnx → Pyramids-1400039.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e0064b18f053e006c3d373c64ff6d5701585350e3104fb4cddbb20da9ac855
+oid sha256:c187d97ca2c574c1b1c52c7395958ce97c89fabe1563f324fd030eda5dcad2f5
 size 1418184

Pyramids/{Pyramids-999917.pt → Pyramids-1400039.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:198600639eba929b15ce56d9a0e005c48067ae9b469a24256091f3d6c76ba86d
+oid sha256:dea949f3cd12a6234cf3d7d73be6a56994ed6e66eb7fefdd3aea39a06a6189f2
 size 8650990

Pyramids/{Pyramids-999917.onnx → Pyramids-499962.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57367ca45735e31371a3d6ba392a3cb121bde32d845cd9780438d53395e08bef
+oid sha256:4955d63fef8e485be4d694d9a91cc3a3d93d9ef9b6bb5513500820cd2e75bd05
 size 1418184

Pyramids/{Pyramids-1028863.pt → Pyramids-499962.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388bfe6bf1337e8e2dff2469da6ce8e47d1b42855b1b58bf3a68565729209388
+oid sha256:98dd9ce86113d69a04ebb90e05955596fbab79f7bf91ccd4ff2ee102fe57e790
 size 8650990

Pyramids/{Pyramids-499894.onnx → Pyramids-999962.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361cdcbbb3ebcac4381be6bfa178dacc7692842c92d9dc13b559145d221ef2fd
+oid sha256:28be9741abecae571027ff870caba24fbf700587ebcfbddf8afe86759049546c
 size 1418184

Pyramids/{Pyramids-499894.pt → Pyramids-999962.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a964f1f00d4970b761474fc4b63d4544e1d2a26e9205686be10d892d43bb1c9
+oid sha256:f8175d98d2bd35576195a3fc534f540833d9dde9f392785162313d5de1da5f31
 size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:388bfe6bf1337e8e2dff2469da6ce8e47d1b42855b1b58bf3a68565729209388
+oid sha256:dea949f3cd12a6234cf3d7d73be6a56994ed6e66eb7fefdd3aea39a06a6189f2
 size 8650990

Pyramids/{events.out.tfevents.1679226763.e9217f9b1f10.49051.0 → events.out.tfevents.1679229486.e9217f9b1f10.60851.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d780ba504aba04044077d4fbc7b731d3079628d78375639d6cc28751dd482185
-size 296454
+oid sha256:a24085c22eb84103666c0167fb92eb49657afbd006db3176ade1304f5d636d43
+size 421214

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": 0.1, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 7000000, "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": 0.1, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1400000, "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": "PyramidsTraining2", "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 7000000
+    max_steps: 1400000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -77,7 +77,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: PyramidsTraining2
   initialize_from: null
   load_model: false
   resume: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 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'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55018 [Flags] 2 [Guid] 603689045 [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] 55243 [Flags] 2 [Guid] 961710937 [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
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2642:(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  0.085 seconds
+- Completed reload, in  0.132 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 +65,17 @@ 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: 0.831603 ms
+UnloadTime: 1.163179 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.
+abort_threads: Failed aborting id: 0x7fbf72366700, mono_thread_manage will ignore it
+
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3493 frames, [32.0 KB-64.0 KB]: 13328 frames, [64.0 KB-128.0 KB]: 2491 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4067 frames, [32.0 KB-64.0 KB]: 16541 frames, [64.0 KB-128.0 KB]: 5659 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 +130,12 @@ 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
@@ -149,7 +148,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -207,28 +206,28 @@ 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]: 19014 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25969 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 13086
+  Peak main deferred allocation count 13122
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 19312 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 26267 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.6 MB
+      Peak Allocated memory 30.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 19313 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.3 MB
+      Peak Allocated memory 22.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +256,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 19312 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26267 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]: 19313 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26268 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,16 +274,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19014 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 25969 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]: 19312 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26267 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
+      Peak Allocated memory 4.3 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,25 +292,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 19313 frames
+      Peak usage frame count: [0-1.0 KB]: 26268 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]: 19313 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 26268 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]: 19313 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 26268 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 28.6 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":1679228947435,"processId":49075,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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":1679232788918,"processId":60875,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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}]}

run_logs/timers.json

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.7547945380210876,
-            "min": 0.7547945380210876,
-            "max": 1.575579047203064,
-            "count": 34
+            "value": 0.2454661726951599,
+            "min": 0.2438683658838272,
+            "max": 1.5889166593551636,
+            "count": 46
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 22547.22265625,
-            "min": 22547.22265625,
-            "max": 47796.765625,
-            "count": 34
+            "value": 7391.4775390625,
+            "min": 7195.09228515625,
+            "max": 48201.375,
+            "count": 46
         },
         "Pyramids.Step.mean": {
-            "value": 1019893.0,
-            "min": 29952.0,
-            "max": 1019893.0,
-            "count": 34
+            "value": 1379901.0,
+            "min": 29910.0,
+            "max": 1379901.0,
+            "count": 46
         },
         "Pyramids.Step.sum": {
-            "value": 1019893.0,
-            "min": 29952.0,
-            "max": 1019893.0,
-            "count": 34
+            "value": 1379901.0,
+            "min": 29910.0,
+            "max": 1379901.0,
+            "count": 46
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5388186573982239,
-            "min": -0.10292333364486694,
-            "max": 0.5979210734367371,
-            "count": 34
+            "value": 0.6779295802116394,
+            "min": -0.09292546659708023,
+            "max": 0.7612824440002441,
+            "count": 46
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 149.7915802001953,
-            "min": -24.804523468017578,
-            "max": 166.81997680664062,
-            "count": 34
+            "value": 193.20993041992188,
+            "min": -22.395036697387695,
+            "max": 227.62344360351562,
+            "count": 46
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.005934992339462042,
-            "min": 0.005030900705605745,
-            "max": 0.28622451424598694,
-            "count": 34
+            "value": 0.06917993724346161,
+            "min": -0.0011057952651754022,
+            "max": 0.3723164498806,
+            "count": 46
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.6499278545379639,
-            "min": 1.2325706481933594,
-            "max": 67.83521270751953,
-            "count": 34
+            "value": 19.71628189086914,
+            "min": -0.2941415309906006,
+            "max": 88.23899841308594,
+            "count": 46
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06820270024996226,
-            "min": 0.06541083514025495,
-            "max": 0.07204974931420195,
-            "count": 34
+            "value": 0.0715606110045753,
+            "min": 0.06373118343569027,
+            "max": 0.07409594399810193,
+            "count": 46
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9548378034994718,
-            "min": 0.46400484936673125,
-            "max": 1.0718769621898365,
-            "count": 34
+            "value": 1.001848554064054,
+            "min": 0.4595870365823242,
+            "max": 1.0637401472389079,
+            "count": 46
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.013333325931427874,
-            "min": 0.0002860417383213954,
-            "max": 0.013954141978611414,
-            "count": 34
+            "value": 0.015125273911204811,
+            "min": 0.0010844276371333522,
+            "max": 0.016129469255813295,
+            "count": 46
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.18666656303999024,
-            "min": 0.003816847432930412,
-            "max": 0.20096884526206207,
-            "count": 34
+            "value": 0.21175383475686735,
+            "min": 0.010844276371333521,
+            "max": 0.24194203883719942,
+            "count": 46
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.00025689698171461634,
-            "min": 0.00025689698171461634,
-            "max": 0.0002993072328839837,
-            "count": 34
+            "value": 7.450995475551021e-06,
+            "min": 7.450995475551021e-06,
+            "max": 0.00029659622562438776,
+            "count": 46
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0035965577440046285,
-            "min": 0.002086762975840914,
-            "max": 0.004201192256745471,
-            "count": 34
+            "value": 0.0001043139366577143,
+            "min": 0.0001043139366577143,
+            "max": 0.0037952302777804277,
+            "count": 46
         },
         "Pyramids.Policy.Epsilon.mean": {
             "value": 0.1,
             "min": 0.09999999999999998,
             "max": 0.10000000000000002,
-            "count": 34
+            "count": 46
         },
         "Pyramids.Policy.Epsilon.sum": {
             "value": 1.4000000000000001,
-            "min": 0.6999999999999998,
+            "min": 0.7,
             "max": 1.5000000000000002,
-            "count": 34
+            "count": 46
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00856466901265306,
-            "min": 0.00856466901265306,
-            "max": 0.00997693084734694,
-            "count": 34
+            "value": 0.0002581149020408164,
+            "min": 0.0002581149020408164,
+            "max": 0.009886654275510205,
+            "count": 46
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.11990536617714284,
-            "min": 0.06955920694857141,
-            "max": 0.14004969883285714,
-            "count": 34
+            "value": 0.0036136086285714296,
+            "min": 0.0036136086285714296,
+            "max": 0.12652116375714287,
+            "count": 46
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.006772161461412907,
-            "min": 0.006772161461412907,
-            "max": 0.377462238073349,
-            "count": 34
+            "value": 0.010419806465506554,
+            "min": 0.010419806465506554,
+            "max": 0.36617204546928406,
+            "count": 46
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.09481026232242584,
-            "min": 0.09481026232242584,
-            "max": 2.64223575592041,
-            "count": 34
+            "value": 0.14587728679180145,
+            "min": 0.14587728679180145,
+            "max": 2.563204288482666,
+            "count": 46
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 341.3292682926829,
-            "min": 341.3292682926829,
+            "value": 262.4824561403509,
+            "min": 242.04132231404958,
             "max": 999.0,
-            "count": 34
+            "count": 46
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 27989.0,
-            "min": 15984.0,
-            "max": 33361.0,
-            "count": 34
+            "value": 29923.0,
+            "min": 16581.0,
+            "max": 33378.0,
+            "count": 46
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6098755960602587,
-            "min": -1.0000000521540642,
-            "max": 1.638465097650539,
-            "count": 34
+            "value": 1.7024122663495833,
+            "min": -0.999962551984936,
+            "max": 1.7566718604648486,
+            "count": 46
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 132.0097988769412,
-            "min": -32.000001668930054,
-            "max": 141.70259851962328,
-            "count": 34
+            "value": 194.0749983638525,
+            "min": -31.998801663517952,
+            "max": 224.85399813950062,
+            "count": 46
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6098755960602587,
-            "min": -1.0000000521540642,
-            "max": 1.638465097650539,
-            "count": 34
+            "value": 1.7024122663495833,
+            "min": -0.999962551984936,
+            "max": 1.7566718604648486,
+            "count": 46
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 132.0097988769412,
-            "min": -32.000001668930054,
-            "max": 141.70259851962328,
-            "count": 34
+            "value": 194.0749983638525,
+            "min": -31.998801663517952,
+            "max": 224.85399813950062,
+            "count": 46
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.024310056237637337,
-            "min": 0.024310056237637337,
-            "max": 7.756379537284374,
-            "count": 34
+            "value": 0.028350559796563812,
+            "min": 0.026500153520542837,
+            "max": 6.862230844357434,
+            "count": 46
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 1.9934246114862617,
-            "min": 1.9934246114862617,
-            "max": 124.10207259654999,
-            "count": 34
+            "value": 3.2319638168082747,
+            "min": 3.1286544502800098,
+            "max": 116.65792435407639,
+            "count": 46
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 34
+            "count": 46
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 34
+            "count": 46
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679226760",
+        "start_time_seconds": "1679229482",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "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=PyramidsTraining2 --no-graphics",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679228947"
+        "end_time_seconds": "1679232788"
     },
-    "total": 2186.592637873,
+    "total": 3306.4794070059997,
     "count": 1,
-    "self": 0.32137707199945,
+    "self": 0.8367734960011148,
     "children": {
         "run_training.setup": {
-            "total": 0.11495052300051611,
+            "total": 0.17392283699882682,
             "count": 1,
-            "self": 0.11495052300051611
+            "self": 0.17392283699882682
         },
         "TrainerController.start_learning": {
-            "total": 2186.156310278,
+            "total": 3305.468710673,
             "count": 1,
-            "self": 1.728721323177524,
+            "self": 2.3896251441310596,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.946259659000134,
+                    "total": 7.0244827779988555,
                     "count": 1,
-                    "self": 5.946259659000134
+                    "self": 7.0244827779988555
                 },
                 "TrainerController.advance": {
-                    "total": 2178.3152930128235,
-                    "count": 65498,
-                    "self": 1.6401526954505243,
+                    "total": 3295.9087750568706,
+                    "count": 90145,
+                    "self": 2.4606926954766095,
                     "children": {
                         "env_step": {
-                            "total": 1527.2603519101176,
-                            "count": 65498,
-                            "self": 1404.0628639380539,
+                            "total": 2407.1799921052516,
+                            "count": 90145,
+                            "self": 2236.1181065479086,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 122.20428043525135,
-                                    "count": 65498,
-                                    "self": 5.09196271251858,
+                                    "total": 169.6538362672436,
+                                    "count": 90145,
+                                    "self": 7.15606690705863,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 117.11231772273277,
-                                            "count": 64376,
-                                            "self": 117.11231772273277
+                                            "total": 162.49776936018498,
+                                            "count": 87560,
+                                            "self": 162.49776936018498
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.993207536812406,
-                                    "count": 65498,
+                                    "total": 1.4080492900993704,
+                                    "count": 90145,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2180.5654558539572,
-                                            "count": 65498,
+                                            "total": 3297.432015708957,
+                                            "count": 90145,
                                             "is_parallel": true,
-                                            "self": 903.2155160336661,
+                                            "self": 1241.269257969976,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018233239989058347,
+                                                            "total": 0.002846290999514167,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005678189991158433,
+                                                            "self": 0.0008743859980313573,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012555049997899914,
+                                                                    "total": 0.00197190500148281,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012555049997899914
+                                                                    "self": 0.00197190500148281
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05015688799903728,
+                                                            "total": 0.05124855100075365,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005839719979121583,
+                                                            "self": 0.0005672670013154857,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00044741700003214646,
+                                                                    "total": 0.00048581000010017306,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00044741700003214646
+                                                                    "self": 0.00048581000010017306
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.047330360001069494,
+                                                                    "total": 0.048365937000198755,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.047330360001069494
+                                                                    "self": 0.048365937000198755
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017951390000234824,
+                                                                    "total": 0.0018295369991392363,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00039197999831230845,
+                                                                    "self": 0.00040743300087342504,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001403159001711174,
+                                                                            "total": 0.0014221039982658112,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001403159001711174
+                                                                            "self": 0.0014221039982658112
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1277.3499398202912,
-                                                    "count": 65497,
+                                                    "total": 2056.162757738981,
+                                                    "count": 90144,
                                                     "is_parallel": true,
-                                                    "self": 32.80185653998706,
+                                                    "self": 46.60205633400801,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.575835734040083,
-                                                            "count": 65497,
+                                                            "total": 33.657413851666206,
+                                                            "count": 90144,
                                                             "is_parallel": true,
-                                                            "self": 23.575835734040083
+                                                            "self": 33.657413851666206
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1124.032802962085,
-                                                            "count": 65497,
+                                                            "total": 1838.478166507315,
+                                                            "count": 90144,
                                                             "is_parallel": true,
-                                                            "self": 1124.032802962085
+                                                            "self": 1838.478166507315
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.939444584179,
-                                                            "count": 65497,
+                                                            "total": 137.42512104599155,
+                                                            "count": 90144,
                                                             "is_parallel": true,
-                                                            "self": 21.012544262603114,
+                                                            "self": 30.324248896702557,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 75.92690032157589,
-                                                                    "count": 523976,
+                                                                    "total": 107.10087214928899,
+                                                                    "count": 721152,
                                                                     "is_parallel": true,
-                                                                    "self": 75.92690032157589
+                                                                    "self": 107.10087214928899
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 649.4147884072554,
-                            "count": 65497,
-                            "self": 3.0295744434133667,
+                            "total": 886.2680902561424,
+                            "count": 90145,
+                            "self": 4.6611480855317495,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 123.7566524708418,
-                                    "count": 65497,
-                                    "self": 123.55744411584237,
+                                    "total": 173.06847194963302,
+                                    "count": 90145,
+                                    "self": 172.8570300576357,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19920835499942768,
+                                            "total": 0.21144189199731045,
                                             "count": 2,
-                                            "self": 0.19920835499942768
+                                            "self": 0.21144189199731045
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 522.6285614930002,
-                                    "count": 456,
-                                    "self": 332.0640753120424,
+                                    "total": 708.5384702209776,
+                                    "count": 641,
+                                    "self": 447.93973490305325,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 190.56448618095783,
-                                            "count": 23484,
-                                            "self": 190.56448618095783
+                                            "total": 260.59873531792437,
+                                            "count": 31875,
+                                            "self": 260.59873531792437
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4559991541318595e-06,
+                    "total": 1.4360011846292764e-06,
                     "count": 1,
-                    "self": 1.4559991541318595e-06
+                    "self": 1.4360011846292764e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.16603482699974847,
+                    "total": 0.14582625799812376,
                     "count": 1,
-                    "self": 0.002033734999713488,
+                    "self": 0.0019542619957064744,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.164001092000035,
+                            "total": 0.1438719960024173,
                             "count": 1,
-                            "self": 0.164001092000035
+                            "self": 0.1438719960024173
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499894,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499894.onnx",
-                "reward": -0.23306669294834137,
-                "creation_time": 1679227761.4740458,
+                "steps": 499962,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-499962.onnx",
+                "reward": 1.733999989926815,
+                "creation_time": 1679230541.8673005,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499894.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-499962.pt"
                 ]
             },
             {
-                "steps": 999917,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999917.onnx",
-                "reward": 1.6816666647791862,
-                "creation_time": 1679228875.0474486,
+                "steps": 999962,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-999962.onnx",
+                "reward": 1.7550000101327896,
+                "creation_time": 1679231760.9252436,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999917.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-999962.pt"
                 ]
             },
             {
-                "steps": 1028863,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1028863.onnx",
-                "reward": 1.733500026166439,
-                "creation_time": 1679228947.1480148,
+                "steps": 1400039,
+                "file_path": "results/PyramidsTraining2/Pyramids/Pyramids-1400039.onnx",
+                "reward": 1.7232857154948371,
+                "creation_time": 1679232788.1541061,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1028863.pt"
+                    "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1028863,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.733500026166439,
-            "creation_time": 1679228947.1480148,
+            "steps": 1400039,
+            "file_path": "results/PyramidsTraining2/Pyramids.onnx",
+            "reward": 1.7232857154948371,
+            "creation_time": 1679232788.1541061,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1028863.pt"
+                "results/PyramidsTraining2/Pyramids/Pyramids-1400039.pt"
             ]
         }
     },