First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d7e400be7ae3ff04c6eef6b676ce21819cc39d184b99b4bf51f0e1985c86df
+oid sha256:e25a61149b9510ef879a5264b41ecf6bca7363fc02becaf9bbbf70a6d11d7c6f
 size 1420238

Pyramids/Pyramids-1999883.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25a61149b9510ef879a5264b41ecf6bca7363fc02becaf9bbbf70a6d11d7c6f
+size 1420238

Pyramids/Pyramids-1999883.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4fca2e04f49ea5d3cd3a4ade653ec54b87e51a3ec5259547c5e979884e9f648
+size 8656252

Pyramids/Pyramids-2000011.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25a61149b9510ef879a5264b41ecf6bca7363fc02becaf9bbbf70a6d11d7c6f
+size 1420238

Pyramids/Pyramids-2000011.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d199c634fafe37af8f506a056e6e1c41de804186a7c5a38bcfed2941a4b64b4
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef0f8bff4b0e9864efb47ade2fdb21295d70305a00bf790cba04a69f01a2a216
+oid sha256:1db98dee929ce99de5c2e5623e191469c4e2c1530ae6501789c37a86e1feaba5
 size 8655778

Pyramids/events.out.tfevents.1717187615.6d7e2a8db8d8.25561.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db20bae683b4ca3b7eb3fddd7c54f4cbe69d64379d4342cacedf5a3e5ae2bc5
+size 111091

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, "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": 1500000, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"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, "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": 2000000, "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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1500000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55326 [Flags] 2 [Guid] 2628174267 [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] 55296 [Flags] 2 [Guid] 3909494079 [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)
@@ -33,17 +33,10 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.090 seconds
+- Completed reload, in  0.131 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)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
-ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
-WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
 WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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?
@@ -65,7 +58,14 @@ 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: 0.833452 ms
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.109154 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.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 1050 frames, [32.0 KB-64.0 KB]: 5620 frames, [64.0 KB-128.0 KB]: 2718 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 753 frames, [32.0 KB-64.0 KB]: 5466 frames, [64.0 KB-128.0 KB]: 3172 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
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 240 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,29 +204,29 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 31 frames, [1.0 MB-2.0 MB]: 9358 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 36 frames, [1.0 MB-2.0 MB]: 9356 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 7324
+  Peak main deferred allocation count 12561
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9388 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 9391 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 24.2 MB
-      Peak Large allocation bytes 0 B
+      Peak Allocated memory 41.4 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9389 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 9391 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.9 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 5.7 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9388 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9391 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]: 9389 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9392 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 69 frames, [1.0 MB-2.0 MB]: 9320 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 56 frames, [1.0 MB-2.0 MB]: 9336 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]: 9388 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9391 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
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9389 frames
+      Peak usage frame count: [0-1.0 KB]: 9392 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]: 9389 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9392 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]: 9389 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 9392 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 29.1 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":1717187516256,"processId":19932,"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":1717188961765,"processId":25594,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3748374879360199,
-            "min": 0.3748374879360199,
-            "max": 0.5130709409713745,
-            "count": 17
+            "value": 0.2930396795272827,
+            "min": 0.2910306751728058,
+            "max": 0.3772023618221283,
+            "count": 16
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 11191.1484375,
-            "min": 10753.966796875,
-            "max": 15011.27734375,
-            "count": 17
+            "value": 8809.9453125,
+            "min": 8684.35546875,
+            "max": 11434.484375,
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 253.2136752136752,
-            "min": 253.2136752136752,
-            "max": 367.75581395348837,
-            "count": 17
+            "value": 248.008547008547,
+            "min": 235.304,
+            "max": 285.65346534653463,
+            "count": 16
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29626.0,
-            "min": 15649.0,
-            "max": 31913.0,
-            "count": 17
+            "value": 29017.0,
+            "min": 28296.0,
+            "max": 31390.0,
+            "count": 16
         },
         "Pyramids.Step.mean": {
-            "value": 1499946.0,
-            "min": 1019944.0,
-            "max": 1499946.0,
-            "count": 17
+            "value": 1979990.0,
+            "min": 1529895.0,
+            "max": 1979990.0,
+            "count": 16
         },
         "Pyramids.Step.sum": {
-            "value": 1499946.0,
-            "min": 1019944.0,
-            "max": 1499946.0,
-            "count": 17
+            "value": 1979990.0,
+            "min": 1529895.0,
+            "max": 1979990.0,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.7240810990333557,
-            "min": 0.5280531644821167,
-            "max": 0.7240810990333557,
-            "count": 17
+            "value": 0.7462483048439026,
+            "min": 0.6567258238792419,
+            "max": 0.8047998547554016,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 212.15576171875,
-            "min": 98.05105590820312,
-            "max": 212.15576171875,
-            "count": 17
+            "value": 219.39700317382812,
+            "min": 187.82357788085938,
+            "max": 243.049560546875,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.015062732622027397,
-            "min": -0.038299426436424255,
-            "max": 0.024049047380685806,
-            "count": 17
+            "value": 0.00307209393940866,
+            "min": -0.03147309273481369,
+            "max": 0.010138324461877346,
+            "count": 16
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -4.4133806228637695,
-            "min": -10.953636169433594,
-            "max": 6.661586284637451,
-            "count": 17
+            "value": 0.9031956195831299,
+            "min": -9.158669471740723,
+            "max": 2.970529079437256,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.7446271010627181,
-            "min": 1.5564873341856331,
-            "max": 1.7446271010627181,
-            "count": 17
+            "value": 1.7343880247611265,
+            "min": 1.6473124828189611,
+            "max": 1.7646959874629975,
+            "count": 16
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 205.86599792540073,
-            "min": 76.35099945962429,
-            "max": 205.86599792540073,
-            "count": 17
+            "value": 202.9233988970518,
+            "min": 173.14899863302708,
+            "max": 220.58699843287468,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.7446271010627181,
-            "min": 1.5564873341856331,
-            "max": 1.7446271010627181,
-            "count": 17
+            "value": 1.7343880247611265,
+            "min": 1.6473124828189611,
+            "max": 1.7646959874629975,
+            "count": 16
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 205.86599792540073,
-            "min": 76.35099945962429,
-            "max": 205.86599792540073,
-            "count": 17
+            "value": 202.9233988970518,
+            "min": 173.14899863302708,
+            "max": 220.58699843287468,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.02108566748581124,
-            "min": 0.02108566748581124,
-            "max": 0.036422244585039495,
-            "count": 17
+            "value": 0.019553067057908904,
+            "min": 0.01902993065235205,
+            "max": 0.024178172263678528,
+            "count": 16
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.4881087633257266,
-            "min": 1.5972690338967368,
-            "max": 3.059468545143318,
-            "count": 17
+            "value": 2.2877088457753416,
+            "min": 2.2583879788508057,
+            "max": 2.7079552935319953,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06781738295600716,
-            "min": 0.06358014467003245,
-            "max": 0.0706216018879786,
-            "count": 17
+            "value": 0.07168206840263437,
+            "min": 0.06593017768768947,
+            "max": 0.07168206840263437,
+            "count": 16
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9494433613841001,
-            "min": 0.6303121379799753,
-            "max": 1.0525073112221435,
-            "count": 17
+            "value": 1.0035489576368812,
+            "min": 0.9230224876276526,
+            "max": 1.0545541316775295,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015996850570073582,
-            "min": 0.012975057341261871,
-            "max": 0.015996850570073582,
-            "count": 17
+            "value": 0.01512822743656221,
+            "min": 0.012747654476932171,
+            "max": 0.016180382961811988,
+            "count": 16
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.22395590798103016,
-            "min": 0.11677551607135683,
-            "max": 0.23405582210398276,
-            "count": 17
+            "value": 0.21179518411187093,
+            "min": 0.1784671626770504,
+            "max": 0.23259178962325677,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.0954703967809542e-06,
-            "min": 3.0954703967809542e-06,
-            "max": 9.788917848140741e-05,
-            "count": 17
+            "value": 5.252037535067855e-06,
+            "min": 5.252037535067855e-06,
+            "max": 7.26182043653857e-05,
+            "count": 16
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 4.333658555493336e-05,
-            "min": 4.333658555493336e-05,
-            "max": 0.0013029187656940667,
-            "count": 17
+            "value": 7.352852549094997e-05,
+            "min": 7.352852549094997e-05,
+            "max": 0.0010166548611153998,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10103179047619049,
-            "min": 0.10103179047619049,
-            "max": 0.13262970370370375,
-            "count": 17
+            "value": 0.10175064642857147,
+            "min": 0.10175064642857147,
+            "max": 0.12420604285714287,
+            "count": 16
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4144450666666668,
-            "min": 1.1936673333333336,
-            "max": 1.9053473333333335,
-            "count": 17
+            "value": 1.4245090500000006,
+            "min": 1.4245090500000006,
+            "max": 1.7511241999999998,
+            "count": 16
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00011307586857142865,
-            "min": 0.00011307586857142865,
-            "max": 0.0032697074000000003,
-            "count": 17
+            "value": 0.00018488957821428565,
+            "min": 0.00018488957821428565,
+            "max": 0.0024281836814285715,
+            "count": 16
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.001583062160000001,
-            "min": 0.001583062160000001,
-            "max": 0.04352716274000001,
-            "count": 17
+            "value": 0.002588454094999999,
+            "min": 0.002588454094999999,
+            "max": 0.033994571540000004,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007952400483191013,
-            "min": 0.007952400483191013,
-            "max": 0.009898611344397068,
-            "count": 17
+            "value": 0.007591236382722855,
+            "min": 0.007591236382722855,
+            "max": 0.008284117095172405,
+            "count": 16
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.11133360862731934,
-            "min": 0.08908750116825104,
-            "max": 0.13826604187488556,
-            "count": 17
+            "value": 0.10627730935811996,
+            "min": 0.10627730935811996,
+            "max": 0.12192925065755844,
+            "count": 16
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 17
+            "count": 16
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 17
+            "count": 16
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1717186256",
+        "start_time_seconds": "1717187613",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "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 --resume",
         "mlagents_version": "1.1.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1717187516"
+        "end_time_seconds": "1717188961"
     },
-    "total": 1259.4383329230004,
+    "total": 1347.8709488369996,
     "count": 1,
-    "self": 0.4760205799993855,
+    "self": 0.71397220200015,
     "children": {
         "run_training.setup": {
-            "total": 0.05126818100052333,
+            "total": 0.07585502799975075,
             "count": 1,
-            "self": 0.05126818100052333
+            "self": 0.07585502799975075
         },
         "TrainerController.start_learning": {
-            "total": 1258.9110441620005,
+            "total": 1347.0811216069997,
             "count": 1,
-            "self": 0.7677809090109804,
+            "self": 0.7859482171006675,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.232809957000427,
+                    "total": 3.318750089999412,
                     "count": 1,
-                    "self": 2.232809957000427
+                    "self": 3.318750089999412
                 },
                 "TrainerController.advance": {
-                    "total": 1255.822123611989,
-                    "count": 32541,
-                    "self": 0.8053479979917029,
+                    "total": 1342.8850223249,
+                    "count": 32833,
+                    "self": 0.8270375527827127,
                     "children": {
                         "env_step": {
-                            "total": 931.4630197449387,
-                            "count": 32541,
-                            "self": 860.8604555749016,
+                            "total": 1011.166429489117,
+                            "count": 32833,
+                            "self": 939.4118349392274,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 70.13547415700396,
-                                    "count": 32541,
-                                    "self": 2.5215686200272103,
+                                    "total": 71.27514389595308,
+                                    "count": 32833,
+                                    "self": 2.551690115922611,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 67.61390553697674,
-                                            "count": 31295,
-                                            "self": 67.61390553697674
+                                            "total": 68.72345378003047,
+                                            "count": 31306,
+                                            "self": 68.72345378003047
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.46709001303315745,
-                                    "count": 32541,
+                                    "total": 0.4794506539365102,
+                                    "count": 32833,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1256.027467099957,
-                                            "count": 32541,
+                                            "total": 1344.0018025109757,
+                                            "count": 32833,
                                             "is_parallel": true,
-                                            "self": 461.83187196688505,
+                                            "self": 473.5056941710782,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021142400000826456,
+                                                            "total": 0.002649463999659929,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006239159993128851,
+                                                            "self": 0.0006987379993006471,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014903240007697605,
+                                                                    "total": 0.001950726000359282,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014903240007697605
+                                                                    "self": 0.001950726000359282
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.088227979000294,
+                                                            "total": 0.04991982699993969,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006633509992752806,
+                                                            "self": 0.0006471659999078838,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005221680003160145,
+                                                                    "total": 0.0005179090003366582,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005221680003160145
+                                                                    "self": 0.0005179090003366582
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08452152000063506,
+                                                                    "total": 0.04695517700019991,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08452152000063506
+                                                                    "self": 0.04695517700019991
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0025209400000676396,
+                                                                    "total": 0.0017995749994952348,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004011549999631825,
+                                                                    "self": 0.00038207599936868064,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.002119785000104457,
+                                                                            "total": 0.0014174990001265542,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.002119785000104457
+                                                                            "self": 0.0014174990001265542
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 794.195595133072,
-                                                    "count": 32540,
+                                                    "total": 870.4961083398975,
+                                                    "count": 32832,
                                                     "is_parallel": true,
-                                                    "self": 17.651247055092426,
+                                                    "self": 17.881733952148352,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 12.197150454011535,
-                                                            "count": 32540,
+                                                            "total": 12.423186172025453,
+                                                            "count": 32832,
                                                             "is_parallel": true,
-                                                            "self": 12.197150454011535
+                                                            "self": 12.423186172025453
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 711.9384423460306,
-                                                            "count": 32540,
+                                                            "total": 786.9438411908104,
+                                                            "count": 32832,
                                                             "is_parallel": true,
-                                                            "self": 711.9384423460306
+                                                            "self": 786.9438411908104
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 52.408755277937416,
-                                                            "count": 32540,
+                                                            "total": 53.247347024913324,
+                                                            "count": 32832,
                                                             "is_parallel": true,
-                                                            "self": 10.992631100058134,
+                                                            "self": 11.437223629844084,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 41.41612417787928,
-                                                                    "count": 260320,
+                                                                    "total": 41.81012339506924,
+                                                                    "count": 262656,
                                                                     "is_parallel": true,
-                                                                    "self": 41.41612417787928
+                                                                    "self": 41.81012339506924
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 323.5537558690585,
-                            "count": 32541,
-                            "self": 1.5293286400828947,
+                            "total": 330.89155528300034,
+                            "count": 32833,
+                            "self": 1.5352185120564172,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 69.16295337697557,
-                                    "count": 32541,
-                                    "self": 69.05397919097504,
+                                    "total": 70.02132520893792,
+                                    "count": 32833,
+                                    "self": 69.90206173393835,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.10897418600052333,
+                                            "total": 0.11926347499957046,
                                             "count": 1,
-                                            "self": 0.10897418600052333
+                                            "self": 0.11926347499957046
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 252.86147385200002,
-                                    "count": 236,
-                                    "self": 149.54518986398216,
+                                    "total": 259.335011562006,
+                                    "count": 237,
+                                    "self": 153.22781376003695,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 103.31628398801786,
-                                            "count": 11364,
-                                            "self": 103.31628398801786
+                                            "total": 106.10719780196905,
+                                            "count": 11400,
+                                            "self": 106.10719780196905
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.002999852062203e-06,
+                    "total": 9.87999555945862e-07,
                     "count": 1,
-                    "self": 1.002999852062203e-06
+                    "self": 9.87999555945862e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0883286810003483,
+                    "total": 0.09139998699993157,
                     "count": 1,
-                    "self": 0.0020003220006401534,
+                    "self": 0.0019656249996842234,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08632835899970814,
+                            "total": 0.08943436200024735,
                             "count": 1,
-                            "self": 0.08632835899970814
+                            "self": 0.08943436200024735
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 999897,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999897.onnx",
-                "reward": null,
-                "creation_time": 1717185953.635213,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999897.pt"
-                ]
-            },
-            {
-                "steps": 1000025,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000025.onnx",
-                "reward": null,
-                "creation_time": 1717185953.7424698,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000025.pt"
-                ]
-            },
             {
                 "steps": 1000025,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000025.onnx",
@@ -45,15 +27,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1500074.pt"
                 ]
+            },
+            {
+                "steps": 1999883,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999883.onnx",
+                "reward": 1.742000013589859,
+                "creation_time": 1717188961.0261059,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999883.pt"
+                ]
+            },
+            {
+                "steps": 2000011,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000011.onnx",
+                "reward": 1.742000013589859,
+                "creation_time": 1717188961.128208,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000011.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1500074,
+            "steps": 2000011,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7529999703168868,
-            "creation_time": 1717187515.8058512,
+            "reward": 1.742000013589859,
+            "creation_time": 1717188961.128208,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1500074.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000011.pt"
             ]
         }
     },