Pyriamds2

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56bc81f8369141e0bc668fe7180026ce193abf39fd060e10cf052d81159f65d1
+oid sha256:e2b5968996ca30102e07382d4495d24d72ec175443a72e92747b351b14f4e75a
 size 1418184

Pyramids/Pyramids-10000029.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b5968996ca30102e07382d4495d24d72ec175443a72e92747b351b14f4e75a
+size 1418184

Pyramids/Pyramids-10000029.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c951bc0fc2a8eb8862bae09c2d752d97a2c1c918922878dd1f17b937cfb04ac
+size 8650990

Pyramids/Pyramids-8499897.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8e64c6c736cd31447d3aaf8d7b48239f6dfc338af9abeed8e2bc2930a38a48
+size 1418184

Pyramids/Pyramids-8499897.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb3f1b1a0a729574b2be830a1923ffcebd6555e18210f173d5d3f5357015da9
+size 8650990

Pyramids/Pyramids-8999993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e99eb0309f55e7ee1b3c1d453049658f3a47353037268f11ce9055e0218d5c
+size 1418184

Pyramids/Pyramids-8999993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74af222e0618d820d84d4e005a35bfaa40bf695485f508f920329b1d95e48f70
+size 8650990

Pyramids/Pyramids-9499898.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c85c0f6f580fd1550ab63bb5460aa3fe0337d68ec217f8f2cdca0a193b069a3
+size 1418184

Pyramids/Pyramids-9499898.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d711738a62a24d5390623eb8cfdc2cda17346714f52dd8e0d5914124a60620a
+size 8650990

Pyramids/Pyramids-9999901.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2b5968996ca30102e07382d4495d24d72ec175443a72e92747b351b14f4e75a
+size 1418184

Pyramids/Pyramids-9999901.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abd2b86392b750e6a0dd621ca19a6658cd4e60d8b64791760442748a86dcdae4
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c83263f1cdb551d8cc6e33d148304981cdba7b259467741a59fb1f1f59eb8e5f
+oid sha256:3c951bc0fc2a8eb8862bae09c2d752d97a2c1c918922878dd1f17b937cfb04ac
 size 8650990

Pyramids/events.out.tfevents.1689708857.arran.455598.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9ffb1893f336ce3564e0cb60b6aa4de322a4a6bacc3609f2f45bb43c0e4e37
+size 2705378

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 10000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -81,7 +81,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 3 interfaces on host : 0) 192.168.8.122 1) 172.17.0.1 2) 192.168.176.1
-Multi-casting "[IP] 192.168.8.122 [Port] 55329 [Flags] 2 [Guid] 3947842651 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.8.122) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 192.168.8.122 [Port] 55502 [Flags] 2 [Guid] 1661159740 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.8.122) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /home/arran/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /home/arran/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /home/arran/huggingface/RL-U5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -16,7 +13,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.048 seconds
+- Completed reload, in  0.061 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)
@@ -48,7 +45,7 @@ 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: 0.480541 ms
+UnloadTime: 0.440596 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 8 worker threads for Enlighten.
@@ -56,7 +53,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 6216 frames, [32.0 KB-64.0 KB]: 10482 frames, [64.0 KB-128.0 KB]: 2072 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 28431 frames, [32.0 KB-64.0 KB]: 92320 frames, [64.0 KB-128.0 KB]: 66762 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
@@ -164,7 +161,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
@@ -211,10 +208,10 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 0]
+    [ALLOC_TEMP_Job.Worker 6]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 5]
       Initial Block Size 256.0 KB
@@ -226,7 +223,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
+    [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -257,28 +254,28 @@ 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]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 187215 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 12850
+  Peak main deferred allocation count 11919
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.9 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 187513 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.1 MB
+      Peak Allocated memory 31.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 187514 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 28.3 MB
+      Peak Allocated memory 27.8 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -305,15 +302,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.9 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 187513 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]: 18771 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 187514 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -323,15 +320,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.9 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 187215 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]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 187513 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
@@ -341,21 +338,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.9 MB
+      Peak Allocated bytes 1.8 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 187514 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]: 18771 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 187514 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: [32.0 KB-64.0 KB]: 18771 frames
+  Peak usage frame count: [32.0 KB-64.0 KB]: 187514 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 38.5 KB
@@ -364,4 +361,4 @@ 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":1689708328791,"processId":449827,"allocatedMemory":2177431,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":206054},{"Thread":34852},{"Manager":18447},{"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":3544},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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":1689718048070,"processId":455655,"allocatedMemory":2177431,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":206054},{"Thread":34852},{"Manager":18447},{"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":3544},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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": 0.38775911927223206,
-            "min": 0.38775911927223206,
-            "max": 1.4447251558303833,
-            "count": 33
+            "value": 0.0955950915813446,
+            "min": 0.09436549991369247,
+            "max": 1.3554917573928833,
+            "count": 333
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 11657.58984375,
-            "min": 11657.58984375,
-            "max": 43827.18359375,
-            "count": 33
+            "value": 2840.3212890625,
+            "min": 2833.984619140625,
+            "max": 41120.19921875,
+            "count": 333
         },
         "Pyramids.Step.mean": {
-            "value": 989873.0,
-            "min": 29952.0,
-            "max": 989873.0,
-            "count": 33
+            "value": 9989901.0,
+            "min": 29980.0,
+            "max": 9989901.0,
+            "count": 333
         },
         "Pyramids.Step.sum": {
-            "value": 989873.0,
-            "min": 29952.0,
-            "max": 989873.0,
-            "count": 33
+            "value": 9989901.0,
+            "min": 29980.0,
+            "max": 9989901.0,
+            "count": 333
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.05246651545166969,
-            "min": -0.0905514657497406,
-            "max": 0.23829002678394318,
-            "count": 33
+            "value": 0.9043908715248108,
+            "min": -0.11052733659744263,
+            "max": 0.9892714023590088,
+            "count": 333
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 12.906763076782227,
-            "min": -21.732351303100586,
-            "max": 60.525665283203125,
-            "count": 33
+            "value": 283.0743408203125,
+            "min": -26.637088775634766,
+            "max": 315.57757568359375,
+            "count": 333
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.5624829530715942,
-            "min": -0.5624829530715942,
-            "max": 0.6832317113876343,
-            "count": 33
+            "value": 0.004980965051800013,
+            "min": -0.045170947909355164,
+            "max": 0.6073437929153442,
+            "count": 333
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -138.3708038330078,
-            "min": -140.74761962890625,
-            "max": 175.59054565429688,
-            "count": 33
+            "value": 1.5590420961380005,
+            "min": -13.280258178710938,
+            "max": 144.54782104492188,
+            "count": 333
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06546499676554376,
-            "min": 0.06546499676554376,
-            "max": 0.07267681104831653,
-            "count": 33
+            "value": 0.06626909062227546,
+            "min": 0.06334194002279435,
+            "max": 0.07505433494494172,
+            "count": 333
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9165099547176128,
-            "min": 0.4796702407824675,
-            "max": 1.0274916140536103,
-            "count": 33
+            "value": 0.9277672687118563,
+            "min": 0.5652185566612553,
+            "max": 1.08269119888713,
+            "count": 333
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.15456800450219024,
-            "min": 0.0009616968275398592,
-            "max": 0.15456800450219024,
-            "count": 33
+            "value": 0.013294236297952013,
+            "min": 0.0004800667355683263,
+            "max": 0.022125206542101213,
+            "count": 333
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 2.1639520630306635,
-            "min": 0.01154036193047831,
-            "max": 2.1639520630306635,
-            "count": 33
+            "value": 0.18611930817132818,
+            "min": 0.0062408675623882425,
+            "max": 0.24089624340801188,
+            "count": 333
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.7901974033e-06,
-            "min": 7.7901974033e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 7.286390428678534e-07,
+            "min": 7.286390428678534e-07,
+            "max": 0.00029952244515918494,
+            "count": 333
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0001090627636462,
-            "min": 0.0001090627636462,
-            "max": 0.0033823475725508994,
-            "count": 33
+            "value": 1.0200946600149948e-05,
+            "min": 1.0200946600149948e-05,
+            "max": 0.004169206010264699,
+            "count": 333
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1025967,
-            "min": 0.1025967,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10024284642857142,
+            "min": 0.10024284642857142,
+            "max": 0.199840815,
+            "count": 333
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4363538,
-            "min": 1.3886848,
-            "max": 2.572478700000001,
-            "count": 33
+            "value": 1.40339985,
+            "min": 1.40339985,
+            "max": 2.8897353000000003,
+            "count": 333
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026941033,
-            "min": 0.00026941033,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 3.4260358214285587e-05,
+            "min": 3.4260358214285587e-05,
+            "max": 0.0099840974185,
+            "count": 333
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0037717446200000006,
-            "min": 0.0037717446200000006,
-            "max": 0.11277216508999999,
-            "count": 33
+            "value": 0.0004796450149999982,
+            "min": 0.0004796450149999982,
+            "max": 0.13898455647,
+            "count": 333
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.016598481684923172,
-            "min": 0.016598481684923172,
-            "max": 0.5532055497169495,
-            "count": 33
+            "value": 0.00384402833878994,
+            "min": 0.0037226839922368526,
+            "max": 0.6547409296035767,
+            "count": 333
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.232378751039505,
-            "min": 0.232378751039505,
-            "max": 3.872438907623291,
-            "count": 33
+            "value": 0.05381639674305916,
+            "min": 0.05211757495999336,
+            "max": 5.237927436828613,
+            "count": 333
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 813.1111111111111,
-            "min": 580.5961538461538,
+            "value": 187.03821656050957,
+            "min": 163.06989247311827,
             "max": 999.0,
-            "count": 33
+            "count": 333
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29272.0,
-            "min": 15984.0,
-            "max": 33423.0,
-            "count": 33
+            "value": 29365.0,
+            "min": 15884.0,
+            "max": 33758.0,
+            "count": 333
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.07543329708278179,
-            "min": -1.0000000521540642,
-            "max": 0.9577384284482553,
-            "count": 33
+            "value": 1.8002203718112533,
+            "min": -0.9999806972280625,
+            "max": 1.8370540386116183,
+            "count": 333
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 2.7155986949801445,
-            "min": -29.93500157445669,
-            "max": 49.80239827930927,
-            "count": 33
+            "value": 282.63459837436676,
+            "min": -30.99940161406994,
+            "max": 339.8549971431494,
+            "count": 333
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.07543329708278179,
-            "min": -1.0000000521540642,
-            "max": 0.9577384284482553,
-            "count": 33
+            "value": 1.8002203718112533,
+            "min": -0.9999806972280625,
+            "max": 1.8370540386116183,
+            "count": 333
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 2.7155986949801445,
-            "min": -29.93500157445669,
-            "max": 49.80239827930927,
-            "count": 33
+            "value": 282.63459837436676,
+            "min": -30.99940161406994,
+            "max": 339.8549971431494,
+            "count": 333
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1388718311053607,
-            "min": 0.11388524502063564,
-            "max": 11.111493222415447,
-            "count": 33
+            "value": 0.00748890871219159,
+            "min": 0.006728075081411737,
+            "max": 15.630076319095679,
+            "count": 333
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 4.999385919792985,
-            "min": 4.950408442469779,
-            "max": 177.78389155864716,
-            "count": 33
+            "value": 1.1757586678140797,
+            "min": 1.1340146101138089,
+            "max": 250.08122110553086,
+            "count": 333
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 333
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 333
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1689707469",
+        "start_time_seconds": "1689708856",
         "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]",
-        "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/home/arran/.local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1689708328"
+        "end_time_seconds": "1689718048"
     },
-    "total": 859.6129147850006,
+    "total": 9191.136063812999,
     "count": 1,
-    "self": 0.21771338100370485,
+    "self": 0.21783762199629564,
     "children": {
         "run_training.setup": {
-            "total": 0.008955823999713175,
+            "total": 0.009290647998568602,
             "count": 1,
-            "self": 0.008955823999713175
+            "self": 0.009290647998568602
         },
         "TrainerController.start_learning": {
-            "total": 859.3862455799972,
+            "total": 9190.908935543004,
             "count": 1,
-            "self": 0.6880475761281559,
+            "self": 7.296172509493772,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2255473999975948,
+                    "total": 2.2592835880059283,
                     "count": 1,
-                    "self": 2.2255473999975948
+                    "self": 2.2592835880059283
                 },
                 "TrainerController.advance": {
-                    "total": 856.4098104708828,
-                    "count": 63352,
-                    "self": 0.644764416050748,
+                    "total": 9181.289401419504,
+                    "count": 658089,
+                    "self": 6.706666782862158,
                     "children": {
                         "env_step": {
-                            "total": 495.48123582721746,
-                            "count": 63352,
-                            "self": 412.2881297392305,
+                            "total": 5506.038501513656,
+                            "count": 658089,
+                            "self": 4669.653360345765,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 82.77501309885702,
-                                    "count": 63352,
-                                    "self": 2.1328031722077867,
+                                    "total": 831.8433572594222,
+                                    "count": 658089,
+                                    "self": 21.683317840346717,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 80.64220992664923,
-                                            "count": 62569,
-                                            "self": 80.64220992664923
+                                            "total": 810.1600394190755,
+                                            "count": 625044,
+                                            "self": 810.1600394190755
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.41809298912994564,
-                                    "count": 63352,
+                                    "total": 4.54178390846937,
+                                    "count": 658089,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 858.3867076142051,
-                                            "count": 63352,
+                                            "total": 9181.73563117189,
+                                            "count": 658089,
                                             "is_parallel": true,
-                                            "self": 492.16968337741855,
+                                            "self": 4984.935508643743,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0010899920016527176,
+                                                            "total": 0.000965316008660011,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002725080121308565,
+                                                            "self": 0.0002711040433496237,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0008174839895218611,
+                                                                    "total": 0.0006942119653103873,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0008174839895218611
+                                                                    "self": 0.0006942119653103873
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02295126400713343,
+                                                            "total": 0.01789177200407721,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00021440500859171152,
+                                                            "self": 0.00021794400527141988,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00020064000273123384,
+                                                                    "total": 0.00022436400467995554,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00020064000273123384
+                                                                    "self": 0.00022436400467995554
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.021891077994951047,
+                                                                    "total": 0.01678669999819249,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.021891077994951047
+                                                                    "self": 0.01678669999819249
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0006451410008594394,
+                                                                    "total": 0.0006627639959333465,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00015810898912604898,
+                                                                    "self": 0.00015804098802618682,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0004870320117333904,
+                                                                            "total": 0.0005047230079071596,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0004870320117333904
+                                                                            "self": 0.0005047230079071596
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 366.21702423678653,
-                                                    "count": 63351,
+                                                    "total": 4196.800122528148,
+                                                    "count": 658088,
                                                     "is_parallel": true,
-                                                    "self": 12.40942198477569,
+                                                    "self": 126.31859621261538,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 9.221894537040498,
-                                                            "count": 63351,
+                                                            "total": 91.8040517183108,
+                                                            "count": 658088,
                                                             "is_parallel": true,
-                                                            "self": 9.221894537040498
+                                                            "self": 91.8040517183108
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 308.2674282877997,
-                                                            "count": 63351,
+                                                            "total": 3603.8484257075324,
+                                                            "count": 658088,
                                                             "is_parallel": true,
-                                                            "self": 308.2674282877997
+                                                            "self": 3603.8484257075324
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 36.31827942717064,
-                                                            "count": 63351,
+                                                            "total": 374.82904888968915,
+                                                            "count": 658088,
                                                             "is_parallel": true,
-                                                            "self": 7.995214811657206,
+                                                            "self": 83.5557382828265,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 28.32306461551343,
-                                                                    "count": 506808,
+                                                                    "total": 291.27331060686265,
+                                                                    "count": 5264704,
                                                                     "is_parallel": true,
-                                                                    "self": 28.32306461551343
+                                                                    "self": 291.27331060686265
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 360.2838102276146,
-                            "count": 63352,
-                            "self": 1.2734898106136825,
+                            "total": 3668.544233122986,
+                            "count": 658089,
+                            "self": 13.930175016677822,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 64.03899535318487,
-                                    "count": 63352,
-                                    "self": 63.902627798190224,
+                                    "total": 710.9470578132459,
+                                    "count": 658089,
+                                    "self": 709.6599365632719,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.13636755499464925,
-                                            "count": 2,
-                                            "self": 0.13636755499464925
+                                            "total": 1.2871212499740068,
+                                            "count": 20,
+                                            "self": 1.2871212499740068
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 294.97132506381604,
-                                    "count": 448,
-                                    "self": 179.79453930055024,
+                                    "total": 2943.6670002930623,
+                                    "count": 4716,
+                                    "self": 1794.112542707604,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 115.1767857632658,
-                                            "count": 22773,
-                                            "self": 115.1767857632658
+                                            "total": 1149.5544575854583,
+                                            "count": 227982,
+                                            "self": 1149.5544575854583
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.409965524449944e-07,
+                    "total": 5.110050551593304e-07,
                     "count": 1,
-                    "self": 5.409965524449944e-07
+                    "self": 5.110050551593304e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.06283959199208766,
+                    "total": 0.06407751499500591,
                     "count": 1,
-                    "self": 0.0007559409859823063,
+                    "self": 0.001261867000721395,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.062083651006105356,
+                            "total": 0.06281564799428452,
                             "count": 1,
-                            "self": 0.062083651006105356
+                            "self": 0.06281564799428452
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499898,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499898.onnx",
-                "reward": 0.028599925339221954,
-                "creation_time": 1689707895.623878,
+                "steps": 8499897,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-8499897.onnx",
+                "reward": 1.8573333074649174,
+                "creation_time": 1689716652.801483,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499898.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-8499897.pt"
                 ]
             },
             {
-                "steps": 999969,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999969.onnx",
-                "reward": -0.1357333908478419,
-                "creation_time": 1689708328.5504286,
+                "steps": 8999993,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-8999993.onnx",
+                "reward": 1.6949999630451202,
+                "creation_time": 1689717117.7614775,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999969.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-8999993.pt"
                 ]
             },
             {
-                "steps": 1000097,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000097.onnx",
-                "reward": -0.1357333908478419,
-                "creation_time": 1689708328.6194544,
+                "steps": 9499898,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9499898.onnx",
+                "reward": 1.798846150820072,
+                "creation_time": 1689717581.5694518,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000097.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-9499898.pt"
+                ]
+            },
+            {
+                "steps": 9999901,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-9999901.onnx",
+                "reward": null,
+                "creation_time": 1689718047.821493,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-9999901.pt"
+                ]
+            },
+            {
+                "steps": 10000029,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-10000029.onnx",
+                "reward": null,
+                "creation_time": 1689718047.891404,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-10000029.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000097,
+            "steps": 10000029,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.1357333908478419,
-            "creation_time": 1689708328.6194544,
+            "reward": null,
+            "creation_time": 1689718047.891404,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000097.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-10000029.pt"
             ]
         }
     },