Trained for another 500_000 stepes

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a66fb0c27202eede6e6212be8c303e014e7aa05d1deed063143ff8b4312771e
+oid sha256:36e75298a2c71b9de1e49ea7a00a734a93b246432db3e7c6b110534e72cd0618
 size 1417437

Pyramids/Pyramids-1000011.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7055b28be37f0d63cb89b4b5ee56767753d34600814c9bc37741f5db0130e470
+oid sha256:dc3a972fbe8e5c689c0127e10e84a1b39667e3021286e1cb9093b693eb59b62b
 size 8652382

Pyramids/{Pyramids-499945.onnx → Pyramids-1499986.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d157603e41efdde41d7b789811ecd2306f3f5993f086ee3cba1824e4660218f
+oid sha256:36e75298a2c71b9de1e49ea7a00a734a93b246432db3e7c6b110534e72cd0618
 size 1417437

Pyramids/{Pyramids-499945.pt → Pyramids-1499986.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a863add520e16fd569c7d43f7816eae2ee0bef1020add978aac82dd6f511c13b
+oid sha256:76ad6f680af726fa08a071d091ff32465f5c109a40b7fcd9fda9b5165cd332a1
 size 8652382

Pyramids/Pyramids-1500114.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e75298a2c71b9de1e49ea7a00a734a93b246432db3e7c6b110534e72cd0618
+size 1417437

Pyramids/Pyramids-1500114.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d2106531e078db3ba33c6e685bcffe01d496d918159cb87f75c93aa5ca6786d
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7055b28be37f0d63cb89b4b5ee56767753d34600814c9bc37741f5db0130e470
+oid sha256:4d2106531e078db3ba33c6e685bcffe01d496d918159cb87f75c93aa5ca6786d
 size 8652382

Pyramids/events.out.tfevents.1674394937.91baf8ef49e7.12034.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e512f52a9b9a68928f73a9d75e5292e5151cf12c852300cec9c008f1c4b9af0
+size 1326

Pyramids/events.out.tfevents.1674394970.91baf8ef49e7.12240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d77d8751b9ab1cfe794f3d54c551838b5de0e0d056f41cba623a8dd4f28dc7
+size 177255

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 1000000
+    max_steps: 1500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -78,8 +78,8 @@ checkpoint_settings:
   run_id: Pyramids Training
   initialize_from: null
   load_model: false
-  resume: false
-  force: true
+  resume: true
+  force: false
   train_model: false
   inference: false
   results_dir: results

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] 55386 [Flags] 2 [Guid] 1539644022 [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] 55067 [Flags] 2 [Guid] 2520474411 [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:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.085 seconds
+- Completed reload, in  0.080 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)
@@ -65,7 +65,7 @@ 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: 0.859218 ms
+UnloadTime: 0.818323 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]: 7567 frames, [32.0 KB-64.0 KB]: 9212 frames, [64.0 KB-128.0 KB]: 1982 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 556 frames, [32.0 KB-64.0 KB]: 6966 frames, [64.0 KB-128.0 KB]: 1875 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
@@ -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]: 299 frames, [1.0 MB-2.0 MB]: 18463 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 33 frames, [1.0 MB-2.0 MB]: 9365 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12527
+  Peak main deferred allocation count 9248
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18759 frames, [32.0 MB-64.0 MB]: 2 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1 frames, [32.0 MB-64.0 MB]: 9397 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 32.6 MB
-      Peak Large allocation bytes 0 B
+      Peak Block count 2
+      Peak Allocated memory 37.9 MB
+      Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18762 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 9397 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.8 MB
-      Peak Large allocation bytes 16.0 MB
+      Peak Allocated memory 7.9 MB
+      Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
   Used Block Count 1
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18761 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9397 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]: 18762 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9398 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 1.6 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18463 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 90 frames, [1.0 MB-2.0 MB]: 9308 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]: 18761 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9397 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
@@ -288,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.6 MB
+      Peak Allocated bytes 1.2 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18762 frames
+      Peak usage frame count: [0-1.0 KB]: 9398 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]: 18762 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9398 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]: 18762 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 9398 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1674394399222,"processId":1657,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1674396060195,"processId":12261,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5198911428451538,
-            "min": 0.49950411915779114,
-            "max": 1.5130971670150757,
-            "count": 33
+            "value": 0.4532043933868408,
+            "min": 0.44381052255630493,
+            "max": 0.5803528428077698,
+            "count": 17
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 15837.9638671875,
-            "min": 14825.2822265625,
-            "max": 45901.31640625,
-            "count": 33
+            "value": 13726.654296875,
+            "min": 10595.9267578125,
+            "max": 17317.728515625,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 432.7313432835821,
+            "min": 394.775,
+            "max": 581.1666666666666,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28993.0,
+            "min": 15791.0,
+            "max": 31863.0,
+            "count": 17
         },
         "Pyramids.Step.mean": {
-            "value": 989993.0,
-            "min": 29952.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1499986.0,
+            "min": 1019938.0,
+            "max": 1499986.0,
+            "count": 17
         },
         "Pyramids.Step.sum": {
-            "value": 989993.0,
-            "min": 29952.0,
-            "max": 989993.0,
-            "count": 33
+            "value": 1499986.0,
+            "min": 1019938.0,
+            "max": 1499986.0,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.28927284479141235,
-            "min": -0.09971584379673004,
-            "max": 0.3005641996860504,
-            "count": 33
+            "value": 0.36165475845336914,
+            "min": 0.2319091558456421,
+            "max": 0.4280426502227783,
+            "count": 17
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 76.65730285644531,
-            "min": -23.93180274963379,
-            "max": 80.85176849365234,
-            "count": 33
+            "value": 96.20016479492188,
+            "min": 59.83256149291992,
+            "max": 113.85934448242188,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.4097687304019928,
-            "min": -0.07940716296434402,
-            "max": 0.4097687304019928,
-            "count": 33
+            "value": 0.035503603518009186,
+            "min": -1.390764832496643,
+            "max": 1.850163459777832,
+            "count": 17
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 108.58871459960938,
-            "min": -20.566455841064453,
-            "max": 108.58871459960938,
-            "count": 33
+            "value": 9.443958282470703,
+            "min": -358.81732177734375,
+            "max": 475.49200439453125,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.477692515102785,
+            "min": 0.9784666348029586,
+            "max": 1.5552099861204625,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 99.0053985118866,
+            "min": 49.901798374950886,
+            "max": 103.12619817256927,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.477692515102785,
+            "min": 0.9784666348029586,
+            "max": 1.5552099861204625,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 99.0053985118866,
+            "min": 49.901798374950886,
+            "max": 103.12619817256927,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.04428825573735078,
+            "min": 0.04428825573735078,
+            "max": 0.07632057223320142,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.9673131344025023,
+            "min": 2.0459056455874816,
+            "max": 4.027543442418391,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06851278855153933,
-            "min": 0.06399466306902468,
-            "max": 0.0745000917061299,
-            "count": 33
+            "value": 0.06789491880183397,
+            "min": 0.06588758243163408,
+            "max": 0.07212834758557225,
+            "count": 17
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9591790397215507,
-            "min": 0.4894855880382907,
-            "max": 1.0474133477837313,
-            "count": 33
+            "value": 0.9505288632256755,
+            "min": 0.6491551282701503,
+            "max": 1.0362443234674479,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.05409306849889276,
-            "min": 4.0460581705471676e-05,
-            "max": 0.05409306849889276,
-            "count": 33
+            "value": 0.016964047471576902,
+            "min": 0.015326032984085646,
+            "max": 0.5244140750891595,
+            "count": 17
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.7573029589844986,
-            "min": 0.0005664481438766034,
-            "max": 0.7573029589844986,
-            "count": 33
+            "value": 0.23749666460207663,
+            "min": 0.21456446177719904,
+            "max": 7.341797051248233,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.554397481900003e-06,
-            "min": 7.554397481900003e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 3.0845275432857135e-06,
+            "min": 3.0845275432857135e-06,
+            "max": 9.787477848620741e-05,
+            "count": 17
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010576156474660004,
-            "min": 0.00010576156474660004,
-            "max": 0.0033727642757452993,
-            "count": 33
+            "value": 4.318338560599999e-05,
+            "min": 4.318338560599999e-05,
+            "max": 0.0013020861659715998,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10251809999999999,
-            "min": 0.10251809999999999,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10102814285714287,
+            "min": 0.10102814285714287,
+            "max": 0.1326249037037037,
+            "count": 17
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4352534,
-            "min": 1.3691136000000002,
-            "max": 2.4843747,
-            "count": 33
+            "value": 1.4143940000000002,
+            "min": 1.1936241333333333,
+            "max": 1.9048849333333338,
+            "count": 17
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002615581900000001,
-            "min": 0.0002615581900000001,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 0.00011271147142857142,
+            "min": 0.00011271147142857142,
+            "max": 0.00326922788,
+            "count": 17
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036618146600000015,
-            "min": 0.0036618146600000015,
-            "max": 0.11244304453,
-            "count": 33
+            "value": 0.0015779605999999998,
+            "min": 0.0015779605999999998,
+            "max": 0.04349943716,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.012860707007348537,
-            "min": 0.012860707007348537,
-            "max": 0.3051005005836487,
-            "count": 33
+            "value": 0.009777999483048916,
+            "min": 0.009777999483048916,
+            "max": 0.01282537542283535,
+            "count": 17
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.18004989624023438,
-            "min": 0.18004989624023438,
-            "max": 2.1357035636901855,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 525.7966101694915,
-            "min": 486.4307692307692,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31022.0,
-            "min": 15984.0,
-            "max": 32628.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.2408930724807854,
-            "min": -1.0000000521540642,
-            "max": 1.359661511847606,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 71.97179820388556,
-            "min": -32.000001668930054,
-            "max": 88.3779982700944,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.2408930724807854,
-            "min": -1.0000000521540642,
-            "max": 1.359661511847606,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 71.97179820388556,
-            "min": -32.000001668930054,
-            "max": 88.3779982700944,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.0703832382618014,
-            "min": 0.06907087514879934,
-            "max": 5.639800105243921,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 4.082227819184482,
-            "min": 3.910407401388511,
-            "max": 90.23680168390274,
-            "count": 33
+            "value": 0.13689199090003967,
+            "min": 0.11162860691547394,
+            "max": 0.18299421668052673,
+            "count": 17
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 17
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1674392394",
+        "start_time_seconds": "1674394967",
         "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
+        "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": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1674394399"
+        "end_time_seconds": "1674396060"
     },
-    "total": 2004.93732439,
+    "total": 1092.667596873,
     "count": 1,
-    "self": 0.4907272739997097,
+    "self": 0.43018394000000626,
     "children": {
         "run_training.setup": {
-            "total": 0.11602225900003305,
+            "total": 0.10236797300012768,
             "count": 1,
-            "self": 0.11602225900003305
+            "self": 0.10236797300012768
         },
         "TrainerController.start_learning": {
-            "total": 2004.330574857,
+            "total": 1092.13504496,
             "count": 1,
-            "self": 1.2359404740082027,
+            "self": 0.6659482690456571,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.5041847640000015,
+                    "total": 6.009644183999626,
                     "count": 1,
-                    "self": 6.5041847640000015
+                    "self": 6.009644183999626
                 },
                 "TrainerController.advance": {
-                    "total": 1996.4962507319915,
-                    "count": 63372,
-                    "self": 1.3625345449779616,
+                    "total": 1085.3672708049548,
+                    "count": 32135,
+                    "self": 0.6634570369433277,
                     "children": {
                         "env_step": {
-                            "total": 1347.6809225329976,
-                            "count": 63372,
-                            "self": 1241.3016295589994,
+                            "total": 759.7270263679825,
+                            "count": 32135,
+                            "self": 706.0505475659379,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 105.61476585896821,
-                                    "count": 63372,
-                                    "self": 4.431706936969533,
+                                    "total": 53.269509911006026,
+                                    "count": 32135,
+                                    "self": 2.2648675340533373,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 101.18305892199868,
-                                            "count": 62538,
-                                            "self": 34.239988891032226,
+                                            "total": 51.00464237695269,
+                                            "count": 31326,
+                                            "self": 17.25952298097218,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 66.94307003096645,
-                                                    "count": 62538,
-                                                    "self": 66.94307003096645
+                                                    "total": 33.74511939598051,
+                                                    "count": 31326,
+                                                    "self": 33.74511939598051
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7645271150299777,
-                                    "count": 63372,
+                                    "total": 0.4069688910385594,
+                                    "count": 32135,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1999.8189732880176,
-                                            "count": 63372,
+                                            "total": 1089.611901268005,
+                                            "count": 32135,
                                             "is_parallel": true,
-                                            "self": 857.3830723300177,
+                                            "self": 434.65522339204836,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021128749999661522,
+                                                            "total": 0.0018921700002465514,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008043959999781691,
+                                                            "self": 0.000711918999968475,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013084789999879831,
+                                                                    "total": 0.0011802510002780764,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013084789999879831
+                                                                    "self": 0.0011802510002780764
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05504090700003417,
+                                                            "total": 0.048748384000191436,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005279830000404218,
+                                                            "self": 0.0005123490004734776,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00045969600000717037,
+                                                                    "total": 0.00054005700030757,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045969600000717037
+                                                                    "self": 0.00054005700030757
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.052219807999961176,
+                                                                    "total": 0.045948587999646406,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.052219807999961176
+                                                                    "self": 0.045948587999646406
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018334200000253986,
+                                                                    "total": 0.001747389999763982,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00047794100004239226,
+                                                                    "self": 0.00042254599975422025,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013554789999830064,
+                                                                            "total": 0.0013248440000097617,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013554789999830064
+                                                                            "self": 0.0013248440000097617
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1142.4359009579998,
-                                                    "count": 63371,
+                                                    "total": 654.9566778759568,
+                                                    "count": 32134,
                                                     "is_parallel": true,
-                                                    "self": 28.05533721107122,
+                                                    "self": 13.927581371995984,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.40451052498247,
-                                                            "count": 63371,
+                                                            "total": 11.930569120969267,
+                                                            "count": 32134,
                                                             "is_parallel": true,
-                                                            "self": 23.40451052498247
+                                                            "self": 11.930569120969267
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 986.6258979329757,
-                                                            "count": 63371,
+                                                            "total": 576.0525423230297,
+                                                            "count": 32134,
                                                             "is_parallel": true,
-                                                            "self": 986.6258979329757
+                                                            "self": 576.0525423230297
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 104.35015528897037,
-                                                            "count": 63371,
+                                                            "total": 53.04598505996182,
+                                                            "count": 32134,
                                                             "is_parallel": true,
-                                                            "self": 22.99482785399931,
+                                                            "self": 11.768339568886404,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 81.35532743497106,
-                                                                    "count": 506968,
+                                                                    "total": 41.27764549107542,
+                                                                    "count": 257072,
                                                                     "is_parallel": true,
-                                                                    "self": 81.35532743497106
+                                                                    "self": 41.27764549107542
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 647.452793654016,
-                            "count": 63372,
-                            "self": 2.174581420992695,
+                            "total": 324.976787400029,
+                            "count": 32135,
+                            "self": 1.2968600550302654,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 147.68340603102484,
-                                    "count": 63372,
-                                    "self": 147.48601828302486,
+                                    "total": 75.45606778799629,
+                                    "count": 32135,
+                                    "self": 75.3409848169963,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19738774799998282,
-                                            "count": 2,
-                                            "self": 0.19738774799998282
+                                            "total": 0.11508297099999254,
+                                            "count": 1,
+                                            "self": 0.11508297099999254
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 497.59480620199844,
-                                    "count": 441,
-                                    "self": 183.79985110600916,
+                                    "total": 248.22385955700247,
+                                    "count": 235,
+                                    "self": 92.66320894699629,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 313.7949550959893,
-                                            "count": 22821,
-                                            "self": 313.7949550959893
+                                            "total": 155.56065061000618,
+                                            "count": 11313,
+                                            "self": 155.56065061000618
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.310001587437e-07,
+                    "total": 9.289997251471505e-07,
                     "count": 1,
-                    "self": 9.310001587437e-07
+                    "self": 9.289997251471505e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09419795600024372,
+                    "total": 0.09218077300010918,
                     "count": 1,
-                    "self": 0.0019760310001402104,
+                    "self": 0.001816039000004821,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09222192500010351,
+                            "total": 0.09036473400010436,
                             "count": 1,
-                            "self": 0.09222192500010351
+                            "self": 0.09036473400010436
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499945,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499945.onnx",
-                "reward": null,
-                "creation_time": 1674393335.4280186,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499945.pt"
-                ]
-            },
             {
                 "steps": 999883,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-999883.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
                 ]
+            },
+            {
+                "steps": 1000011,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000011.onnx",
+                "reward": null,
+                "creation_time": 1674394940.9346263,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
+                ]
+            },
+            {
+                "steps": 1499986,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499986.onnx",
+                "reward": 1.7127499841153622,
+                "creation_time": 1674396059.614464,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499986.pt"
+                ]
+            },
+            {
+                "steps": 1500114,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500114.onnx",
+                "reward": 1.7127499841153622,
+                "creation_time": 1674396059.8315725,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500114.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000011,
+            "steps": 1500114,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5799999684095383,
-            "creation_time": 1674394398.782489,
+            "reward": 1.7127499841153622,
+            "creation_time": 1674396059.8315725,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1500114.pt"
             ]
         }
     },