First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11b498a7286dc1cdee818015e0753fc4ca6447073b82215ee05a77a4310789de
+oid sha256:55508ff2fdab8418cf64efddac78b09a867034f9d97e7d1fe22b736501406b84
 size 1420238

Pyramids/Pyramids-369986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb1ee069cff1fa76cdd5b8299474830f915b3cb7e746901db19f7cd587b77ca
+size 1420238

Pyramids/Pyramids-369986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda040b60416fffe3cc56d4e2a037c3f66a597cedde5f3c3cab95a83dd90a39e
+size 8656000

Pyramids/Pyramids-379929.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58caa1f400f72c9f617f203c0a1da83b057f356bf94e55af2c7460473d9a4f59
+size 1420238

Pyramids/Pyramids-379929.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0152fd25fdbbc42dfa36f4e683df733634be9f74290450b45c2d04c1f31d60
+size 8656000

Pyramids/Pyramids-389912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6993c3a4e9b5c554657b57c5180fa3ce6e5da809a2c61b16a4cee423b96ab0f
+size 1420238

Pyramids/Pyramids-389912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c773a429e6e6b2170ab4196f2d4dd57783af7679cb345087cab2d93a6bb53b
+size 8656000

Pyramids/Pyramids-399964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f677378fa5269aba38189ae961b04e38b21aa4cee61043fc73367a80393482a2
+size 1420238

Pyramids/Pyramids-399964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a432cfa8e64d971d2fd8148a73fe855f79750aad178206f4aa6f2664d1c09f2
+size 8656000

Pyramids/Pyramids-405447.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55508ff2fdab8418cf64efddac78b09a867034f9d97e7d1fe22b736501406b84
+size 1420238

Pyramids/Pyramids-405447.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30622ff4fd3872f116c5e6e6771b69ac5c896e7a3df2e335653c97c9753780a6
+size 8656000

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fda7957128f27ee58c423998659c819fbea64d68627e704d1128b64aab4a5fe
+oid sha256:e6f63bf9c082908e810110afc8e97c909a65fd7a60006a20ae30ae4c2e3ce5ba
 size 8655605

Pyramids/events.out.tfevents.1772325576.0e9230f42a0c.13994.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb860eb23cd9bf2de0759896ba9a9dc3fedf1abfd92f5b25574654ee89c8eab4
+size 1422

Pyramids/events.out.tfevents.1772325621.0e9230f42a0c.14378.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64fb5ab44215e8ade4de65200499d868afb39c3a50f89514a8f1318cfc547951
+size 23111

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 384, "buffer_size": 2048, "learning_rate": 0.0006, "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": 10000, "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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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 Training1", "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": 384, "buffer_size": 2048, "learning_rate": 0.0006, "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": 10000, "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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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 Training1", "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

@@ -82,7 +82,7 @@ checkpoint_settings:
   run_id: Pyramids Training1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: 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] 55329 [Flags] 2 [Guid] 1791771930 [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] 55297 [Flags] 2 [Guid] 1534125700 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c: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  0.096 seconds
+- Completed reload, in  0.088 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,15 +65,20 @@ 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: 1.113629 ms
+UnloadTime: 0.833994 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.
 PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 3526 frames, [32.0 KB-64.0 KB]: 1825 frames, [64.0 KB-128.0 KB]: 348 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 968 frames, [32.0 KB-64.0 KB]: 592 frames, [64.0 KB-128.0 KB]: 144 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
@@ -118,11 +123,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AUDIO_FMOD stream thread]
-      Initial Block Size 64.0 KB
-      Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -204,28 +204,28 @@ 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]: 5401 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 207 frames, [1.0 MB-2.0 MB]: 1498 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.5 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11554
+  Peak main deferred allocation count 12588
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 5699 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1704 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.6 MB
+      Peak Allocated memory 30.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 5700 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1705 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.0 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
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 5699 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1704 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]: 5700 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1705 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 5401 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 298 frames, [1.0 MB-2.0 MB]: 1407 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]: 5699 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1704 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
@@ -288,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 5700 frames
+      Peak usage frame count: [0-1.0 KB]: 1705 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]: 5700 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1705 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]: 5700 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1705 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 27.4 KB
@@ -311,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1772325107485,"processId":9033,"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":1772325812200,"processId":14402,"allocatedMemory":1970545,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":11015},{"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": 0.48718133568763733,
-            "min": 0.44092342257499695,
-            "max": 1.3449426889419556,
-            "count": 10
+            "value": 0.6047596335411072,
+            "min": 0.5095651149749756,
+            "max": 0.6047596335411072,
+            "count": 3
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 14771.337890625,
-            "min": 13051.3330078125,
-            "max": 40800.1796875,
-            "count": 10
+            "value": 18007.322265625,
+            "min": 7737.23681640625,
+            "max": 18007.322265625,
+            "count": 3
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 884.2894736842105,
+            "min": 356.3333333333333,
+            "max": 912.2972972972973,
+            "count": 3
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 33603.0,
+            "min": 1069.0,
+            "max": 33755.0,
+            "count": 3
         },
         "Pyramids.Step.mean": {
-            "value": 299997.0,
-            "min": 29900.0,
-            "max": 299997.0,
-            "count": 10
+            "value": 389912.0,
+            "min": 329903.0,
+            "max": 389912.0,
+            "count": 3
         },
         "Pyramids.Step.sum": {
-            "value": 299997.0,
-            "min": 29900.0,
-            "max": 299997.0,
-            "count": 10
+            "value": 389912.0,
+            "min": 329903.0,
+            "max": 389912.0,
+            "count": 3
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.011249717324972153,
-            "min": -0.09220730513334274,
-            "max": 0.11397071927785873,
-            "count": 10
+            "value": 0.0014005752746015787,
+            "min": -0.011956916190683842,
+            "max": 0.042571861296892166,
+            "count": 3
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -2.756180763244629,
-            "min": -22.221960067749023,
-            "max": 27.01106071472168,
-            "count": 10
+            "value": 0.34174036979675293,
+            "min": -2.917487621307373,
+            "max": 4.810620307922363,
+            "count": 3
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.08842242509126663,
-            "min": 0.08842242509126663,
-            "max": 0.7224162220954895,
-            "count": 10
+            "value": 0.055230408906936646,
+            "min": 0.055230408906936646,
+            "max": 0.08339454233646393,
+            "count": 3
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 21.663494110107422,
-            "min": 21.663494110107422,
-            "max": 174.82472229003906,
-            "count": 10
+            "value": 13.47622013092041,
+            "min": 9.423583030700684,
+            "max": 18.219188690185547,
+            "count": 3
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.4112105710726035,
+            "min": -0.5887297756365828,
+            "max": 1.6436666597922642,
+            "count": 3
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -15.626001700758934,
+            "min": -21.783001698553562,
+            "max": 4.930999979376793,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.4112105710726035,
+            "min": -0.5887297756365828,
+            "max": 1.6436666597922642,
+            "count": 3
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -15.626001700758934,
+            "min": -21.783001698553562,
+            "max": 4.930999979376793,
+            "count": 3
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.5639805650142463,
+            "min": 0.29365531479318935,
+            "max": 0.694428773345174,
+            "count": 3
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 21.431261470541358,
+            "min": 0.8809659443795681,
+            "max": 25.69386461377144,
+            "count": 3
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.03467328250997178,
-            "min": 0.03386264300712175,
-            "max": 0.04452162305889133,
-            "count": 10
+            "value": 0.03770318213991523,
+            "min": 0.03608820921941422,
+            "max": 0.04011000821211686,
+            "count": 3
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.48542595513960496,
-            "min": 0.35617298447113066,
-            "max": 0.5592456866828017,
-            "count": 10
+            "value": 0.5278445499588131,
+            "min": 0.2005500410605843,
+            "max": 0.5278445499588131,
+            "count": 3
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0054510476872175265,
-            "min": 0.0009858210122475693,
-            "max": 0.019210243828085907,
-            "count": 10
+            "value": 0.0046561986083825295,
+            "min": 0.0032859840574532523,
+            "max": 0.005008314605414246,
+            "count": 3
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.07631466762104537,
-            "min": 0.012923946980218818,
-            "max": 0.15368195062468726,
-            "count": 10
+            "value": 0.06518678051735541,
+            "min": 0.02504157302707123,
+            "max": 0.06518678051735541,
+            "count": 3
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 0.00042893711422477135,
-            "min": 0.00042893711422477135,
-            "max": 0.0005895222767462874,
-            "count": 10
+            "value": 0.0003751977374670499,
+            "min": 0.0003751977374670499,
+            "max": 0.0004061731523044799,
+            "count": 3
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.006005119599146799,
-            "min": 0.0047161782139702995,
-            "max": 0.007017206630465599,
-            "count": 10
+            "value": 0.0052527683245386985,
+            "min": 0.0020308657615223996,
+            "max": 0.0052527683245386985,
+            "count": 3
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.17148951428571427,
-            "min": 0.17148951428571427,
-            "max": 0.1982537125,
-            "count": 10
+            "value": 0.16253294999999998,
+            "min": 0.16253294999999998,
+            "max": 0.16769552000000001,
+            "count": 3
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 2.4008532,
-            "min": 1.5860297,
-            "max": 2.5695344,
-            "count": 10
+            "value": 2.2754613,
+            "min": 0.8384776,
+            "max": 2.2754613,
+            "count": 3
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.007151802477142857,
-            "min": 0.007151802477142857,
-            "max": 0.009825545878750001,
-            "count": 10
+            "value": 0.006257041705,
+            "min": 0.006257041705,
+            "max": 0.006772782448000001,
+            "count": 3
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.10012523468,
-            "min": 0.07860436703000001,
-            "max": 0.11697648656,
-            "count": 10
+            "value": 0.08759858387,
+            "min": 0.03386391224,
+            "max": 0.08759858387,
+            "count": 3
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.09631339460611343,
-            "min": 0.09631339460611343,
-            "max": 0.9355165958404541,
-            "count": 10
+            "value": 0.05999378487467766,
+            "min": 0.05999378487467766,
+            "max": 0.08059360086917877,
+            "count": 3
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 1.3483874797821045,
-            "min": 1.3483874797821045,
-            "max": 7.484132766723633,
-            "count": 10
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 906.0571428571428,
-            "min": 895.5555555555555,
-            "max": 999.0,
-            "count": 10
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31712.0,
-            "min": 17466.0,
-            "max": 32713.0,
-            "count": 10
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.3351657609854426,
-            "min": -0.9998600512742997,
-            "max": -0.30345930214281436,
-            "count": 10
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -11.73080163449049,
-            "min": -30.995201587677002,
-            "max": -8.193401157855988,
-            "count": 10
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.3351657609854426,
-            "min": -0.9998600512742997,
-            "max": -0.30345930214281436,
-            "count": 10
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -11.73080163449049,
-            "min": -30.995201587677002,
-            "max": -8.193401157855988,
-            "count": 10
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.9231859935181481,
-            "min": 0.9231859935181481,
-            "max": 11.578956580824322,
-            "count": 10
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 32.311509773135185,
-            "min": 28.336788680404425,
-            "max": 247.3644058406353,
-            "count": 10
+            "value": 0.839913010597229,
+            "min": 0.40296801924705505,
+            "max": 0.9192857146263123,
+            "count": 3
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 3
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 10
+            "count": 3
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1772324510",
+        "start_time_seconds": "1772325620",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training1 --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+cu128",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1772325107"
+        "end_time_seconds": "1772325812"
     },
-    "total": 597.4701588340001,
+    "total": 191.86818165799968,
     "count": 1,
-    "self": 0.6499863020001158,
+    "self": 0.544326682999781,
     "children": {
         "run_training.setup": {
-            "total": 0.024338695000096777,
+            "total": 0.02278858499994385,
             "count": 1,
-            "self": 0.024338695000096777
+            "self": 0.02278858499994385
         },
         "TrainerController.start_learning": {
-            "total": 596.7958338369999,
+            "total": 191.30106638999996,
             "count": 1,
-            "self": 0.4535029420094361,
+            "self": 0.14137196499905258,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.920888082999909,
+                    "total": 2.2871534360001533,
                     "count": 1,
-                    "self": 2.920888082999909
+                    "self": 2.2871534360001533
                 },
                 "TrainerController.advance": {
-                    "total": 593.0715385539904,
-                    "count": 19124,
-                    "self": 0.46691838498054494,
+                    "total": 188.54476596300083,
+                    "count": 5724,
+                    "self": 0.13980247200515805,
                     "children": {
                         "env_step": {
-                            "total": 451.1742693780134,
-                            "count": 19124,
-                            "self": 399.02851400802,
+                            "total": 144.46161838900707,
+                            "count": 5724,
+                            "self": 128.98554180700103,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 51.853985225991664,
-                                    "count": 19124,
-                                    "self": 1.4880065949726031,
+                                    "total": 15.391121884000768,
+                                    "count": 5724,
+                                    "self": 0.4556561900158158,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 50.36597863101906,
-                                            "count": 19000,
-                                            "self": 50.36597863101906
+                                            "total": 14.935465693984952,
+                                            "count": 5682,
+                                            "self": 14.935465693984952
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.29177014400170265,
-                                    "count": 19124,
+                                    "total": 0.08495469800527644,
+                                    "count": 5723,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 593.6382533730057,
-                                            "count": 19124,
+                                            "total": 190.27273671499324,
+                                            "count": 5723,
                                             "is_parallel": true,
-                                            "self": 232.91384954699197,
+                                            "self": 72.78986654099162,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002400254999884055,
+                                                            "total": 0.0017274550000365707,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006844129998171411,
+                                                            "self": 0.000502880000112782,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001715842000066914,
+                                                                    "total": 0.0012245749999237887,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001715842000066914
+                                                                    "self": 0.0012245749999237887
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.11202883600003588,
+                                                            "total": 0.046910996999940835,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005162520001249504,
+                                                            "self": 0.0005484629996317381,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004278869998870505,
+                                                                    "total": 0.0004600199999913457,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004278869998870505
+                                                                    "self": 0.0004600199999913457
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.10750669499998367,
+                                                                    "total": 0.04431175300032919,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.10750669499998367
+                                                                    "self": 0.04431175300032919
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0035780020000402146,
+                                                                    "total": 0.0015907609999885608,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0023702869998487586,
+                                                                    "self": 0.00035157999946022755,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001207715000191456,
+                                                                            "total": 0.0012391810005283332,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001207715000191456
+                                                                            "self": 0.0012391810005283332
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 360.7244038260137,
-                                                    "count": 19123,
+                                                    "total": 117.48287017400162,
+                                                    "count": 5722,
                                                     "is_parallel": true,
-                                                    "self": 10.391553950986918,
+                                                    "self": 3.138499505024811,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 6.915995956998813,
-                                                            "count": 19123,
+                                                            "total": 2.079545742980372,
+                                                            "count": 5722,
                                                             "is_parallel": true,
-                                                            "self": 6.915995956998813
+                                                            "self": 2.079545742980372
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 309.65846909999937,
-                                                            "count": 19123,
+                                                            "total": 102.1327059909836,
+                                                            "count": 5722,
                                                             "is_parallel": true,
-                                                            "self": 309.65846909999937
+                                                            "self": 102.1327059909836
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 33.75838481802862,
-                                                            "count": 19123,
+                                                            "total": 10.13211893501284,
+                                                            "count": 5722,
                                                             "is_parallel": true,
-                                                            "self": 7.371057496071444,
+                                                            "self": 2.164201819016398,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 26.387327321957173,
-                                                                    "count": 152984,
+                                                                    "total": 7.967917115996443,
+                                                                    "count": 45776,
                                                                     "is_parallel": true,
-                                                                    "self": 26.387327321957173
+                                                                    "self": 7.967917115996443
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 141.4303507909965,
-                            "count": 19124,
-                            "self": 0.7637092439968001,
+                            "total": 43.9433451019886,
+                            "count": 5723,
+                            "self": 0.2177785349927035,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 39.89908687100046,
-                                    "count": 19124,
-                                    "self": 37.325428843000054,
+                                    "total": 12.358881188995383,
+                                    "count": 5723,
+                                    "self": 11.613662805996228,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 2.573658028000409,
-                                            "count": 30,
-                                            "self": 2.573658028000409
+                                            "total": 0.7452183829991554,
+                                            "count": 9,
+                                            "self": 0.7452183829991554
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 100.76755467599924,
-                                    "count": 128,
-                                    "self": 72.64264833798234,
+                                    "total": 31.36668537800051,
+                                    "count": 39,
+                                    "self": 22.758413228997597,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 28.1249063380169,
-                                            "count": 2142,
-                                            "self": 28.1249063380169
+                                            "total": 8.608272149002914,
+                                            "count": 627,
+                                            "self": 8.608272149002914
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.6220001270994544e-06,
+                    "total": 1.416000031895237e-06,
                     "count": 1,
-                    "self": 1.6220001270994544e-06
+                    "self": 1.416000031895237e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.34990263600002436,
+                    "total": 0.3277736099998947,
                     "count": 1,
-                    "self": 0.007713586000136274,
+                    "self": 0.0018258170002809493,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.3421890499998881,
+                            "total": 0.32594779299961374,
                             "count": 1,
-                            "self": 0.3421890499998881
+                            "self": 0.32594779299961374
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,58 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 269914,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-269914.onnx",
+                "steps": 369986,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-369986.onnx",
                 "reward": null,
-                "creation_time": 1772325041.706568,
+                "creation_time": 1772325737.5484123,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-269914.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-369986.pt"
                 ]
             },
             {
-                "steps": 279912,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-279912.onnx",
-                "reward": null,
-                "creation_time": 1772325061.52339,
+                "steps": 379929,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-379929.onnx",
+                "reward": -1.0000000521540642,
+                "creation_time": 1772325758.5961177,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-279912.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-379929.pt"
                 ]
             },
             {
-                "steps": 289923,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-289923.onnx",
-                "reward": 0.6803999791542689,
-                "creation_time": 1772325081.5630383,
+                "steps": 389912,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-389912.onnx",
+                "reward": -0.999800056219101,
+                "creation_time": 1772325778.052588,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-289923.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-389912.pt"
                 ]
             },
             {
-                "steps": 299997,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-299997.onnx",
+                "steps": 399964,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-399964.onnx",
                 "reward": null,
-                "creation_time": 1772325100.941728,
+                "creation_time": 1772325800.6291623,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-299997.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-399964.pt"
                 ]
             },
             {
-                "steps": 303333,
-                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-303333.onnx",
-                "reward": null,
-                "creation_time": 1772325106.9032443,
+                "steps": 405447,
+                "file_path": "results/Pyramids Training1/Pyramids/Pyramids-405447.onnx",
+                "reward": 1.5904999747872353,
+                "creation_time": 1772325811.693388,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training1/Pyramids/Pyramids-303333.pt"
+                    "results/Pyramids Training1/Pyramids/Pyramids-405447.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 303333,
+            "steps": 405447,
             "file_path": "results/Pyramids Training1/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1772325106.9032443,
+            "reward": 1.5904999747872353,
+            "creation_time": 1772325811.693388,
             "auxillary_file_paths": [
-                "results/Pyramids Training1/Pyramids/Pyramids-303333.pt"
+                "results/Pyramids Training1/Pyramids/Pyramids-405447.pt"
             ]
         }
     },