First Commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab76005576dc0e64a54f4b8c62c7df03638017b0e2791bf2a24ca764a80bdb9d
+oid sha256:750f4f711c31b35c0c6ae69ced9280267f9332a1ed4aa6253e2b206e29dacf92
 size 1418184

Pyramids/{Pyramids-100369.onnx → Pyramids-1499928.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27546e534101f556b8705dde1d8ed44305895d2fccb79c7bf9f21449fdc8772
+oid sha256:750f4f711c31b35c0c6ae69ced9280267f9332a1ed4aa6253e2b206e29dacf92
 size 1418184

Pyramids/{Pyramids-100369.pt → Pyramids-1499928.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104cc77065e9d5a34eeb67190ad237384fbf0632a784cb117518b5d22f99cd19
+oid sha256:01ff480835bf514e4c1b2594ae5911c7d5820f02f476864aa8aee262e252d65d
 size 8650158

Pyramids/{Pyramids-40192.onnx → Pyramids-1500056.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e93d0aa54b0abb958aada9b4e5c18b94c7c87347d3d46bbe8430a6d269986c5
+oid sha256:750f4f711c31b35c0c6ae69ced9280267f9332a1ed4aa6253e2b206e29dacf92
 size 1418184

Pyramids/{Pyramids-40192.pt → Pyramids-1500056.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff15b977de0fba9c845f4c3b0d57e94d14e1707bf06eb582dab90b98f525375
+oid sha256:5a8b74d5ee9094356fa2b0aee5aa70a9a82a8df879e0d6c917dbf2c17ffd275f
 size 8650158

Pyramids/Pyramids-999901.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff853300b6f2063fd317311ec10d5b939a64426fd622f22ddd2d25cc103ad42f
+size 1418184

Pyramids/Pyramids-999901.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6546130a6bdf3146e32c8a449423866d1b2b0496ae9dd4307fd08457d17e548a
+size 8650158

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801a1335cb0da12fbaeb1edf2cd50f76de5c9b5dd91dba45205205e795f77e8f
+oid sha256:5a8b74d5ee9094356fa2b0aee5aa70a9a82a8df879e0d6c917dbf2c17ffd275f
 size 8650158

Pyramids/events.out.tfevents.1679882074.3bb84cbeccac.21695.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:949c2dd3dbeede1331facf30af8804b8a8015044497354b139476f47a81b7026
+size 343742

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": 500000, "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}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 500000
+    max_steps: 1500000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55159 [Flags] 2 [Guid] 1425935697 [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] 55237 [Flags] 2 [Guid] 2034800991 [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  0.114 seconds
+- Completed reload, in  0.108 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: 1.081347 ms
+UnloadTime: 1.047577 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]: 4649 frames, [32.0 KB-64.0 KB]: 2271 frames, [64.0 KB-128.0 KB]: 588 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 6108 frames, [32.0 KB-64.0 KB]: 8698 frames, [64.0 KB-128.0 KB]: 3958 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
@@ -128,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -146,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 7210 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 92 frames, [1.0 MB-2.0 MB]: 18673 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.4 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11550
+  Peak main deferred allocation count 8108
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 7508 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18764 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 31.9 MB
+      Peak Allocated memory 26.8 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 7509 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.7 MB
+      Peak Allocated memory 23.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 7508 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 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]: 7509 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 7210 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 235 frames, [1.0 MB-2.0 MB]: 18530 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]: 7508 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -288,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 7509 frames
+      Peak usage frame count: [0-1.0 KB]: 18765 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]: 7509 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18765 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]: 7509 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18765 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -311,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679881857205,"processId":15836,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679885401104,"processId":21714,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6851799488067627,
-            "min": 0.6851799488067627,
-            "max": 1.0732108354568481,
-            "count": 13
+            "value": 0.29890257120132446,
+            "min": 0.2798689603805542,
+            "max": 0.690678060054779,
+            "count": 34
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 20665.02734375,
-            "min": 20665.02734375,
-            "max": 30553.39453125,
-            "count": 13
+            "value": 8947.947265625,
+            "min": 6837.51416015625,
+            "max": 20687.189453125,
+            "count": 34
         },
         "Pyramids.Step.mean": {
-            "value": 479973.0,
-            "min": 119953.0,
-            "max": 479973.0,
-            "count": 13
+            "value": 1499928.0,
+            "min": 509984.0,
+            "max": 1499928.0,
+            "count": 34
         },
         "Pyramids.Step.sum": {
-            "value": 479973.0,
-            "min": 119953.0,
-            "max": 479973.0,
-            "count": 13
+            "value": 1499928.0,
+            "min": 509984.0,
+            "max": 1499928.0,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.04727970436215401,
-            "min": -0.09163922071456909,
-            "max": -0.018209222704172134,
-            "count": 13
+            "value": 0.6424160599708557,
+            "min": -0.07951540499925613,
+            "max": 0.7126874327659607,
+            "count": 34
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -11.441688537597656,
-            "min": -21.90177345275879,
-            "max": -4.461259365081787,
-            "count": 13
+            "value": 183.0885772705078,
+            "min": -19.163211822509766,
+            "max": 209.5301055908203,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.02514275163412094,
-            "min": 0.019109051674604416,
-            "max": 0.084037646651268,
-            "count": 13
+            "value": -0.006785540841519833,
+            "min": -0.012906786054372787,
+            "max": 0.03882264718413353,
+            "count": 34
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.084546089172363,
-            "min": 4.624390602111816,
-            "max": 14.788856506347656,
-            "count": 13
+            "value": -1.9338791370391846,
+            "min": -3.639713764190674,
+            "max": 10.443291664123535,
+            "count": 34
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 300.40776699029124,
+            "min": 158.0,
+            "max": 972.09375,
+            "count": 34
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30942.0,
+            "min": 474.0,
+            "max": 33200.0,
+            "count": 34
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.680166977267821,
+            "min": -0.7852750485762954,
+            "max": 1.8419999827941258,
+            "count": 34
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 173.05719865858555,
+            "min": -25.128801554441452,
+            "max": 195.44419772922993,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.680166977267821,
+            "min": -0.7852750485762954,
+            "max": 1.8419999827941258,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 173.05719865858555,
+            "min": -25.128801554441452,
+            "max": 195.44419772922993,
+            "count": 34
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.031643046891880196,
+            "min": 0.029883607279324473,
+            "max": 0.17481861807382068,
+            "count": 34
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.2592338298636605,
+            "min": 0.14030545111745596,
+            "max": 6.817926104879007,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06645620250728775,
-            "min": 0.06553690842359469,
-            "max": 0.07159876862969432,
-            "count": 13
+            "value": 0.06658352132720667,
+            "min": 0.06625723796691198,
+            "max": 0.07332178857824248,
+            "count": 34
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9303868351020284,
-            "min": 0.265779438362679,
-            "max": 1.047773662234249,
-            "count": 13
+            "value": 0.9321692985808934,
+            "min": 0.21996536573472744,
+            "max": 1.0763413148992649,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.002682014867945663,
-            "min": 0.00020303111836860016,
-            "max": 0.005888134813581385,
-            "count": 13
+            "value": 0.01617559841306553,
+            "min": 0.0017751062543497832,
+            "max": 0.01617559841306553,
+            "count": 34
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.037548208151239285,
-            "min": 0.002436373420423202,
-            "max": 0.07422052906208682,
-            "count": 13
+            "value": 0.2264583777829174,
+            "min": 0.0211898731298182,
+            "max": 0.23511970965288737,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.052922172838571e-05,
-            "min": 2.052922172838571e-05,
-            "max": 0.0002336922221026,
-            "count": 13
+            "value": 3.1718132284761884e-06,
+            "min": 3.1718132284761884e-06,
+            "max": 0.0001991639002787111,
+            "count": 34
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0002874091041973999,
-            "min": 0.0002874091041973999,
-            "max": 0.0024146931951024003,
-            "count": 13
+            "value": 4.440538519866664e-05,
+            "min": 4.440538519866664e-05,
+            "max": 0.0027301714899430002,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10684304285714284,
-            "min": 0.10684304285714284,
-            "max": 0.1778974,
-            "count": 13
+            "value": 0.10105723809523813,
+            "min": 0.10105723809523813,
+            "max": 0.16638795555555558,
+            "count": 34
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4958025999999998,
-            "min": 0.7115896,
-            "max": 2.013959,
-            "count": 13
+            "value": 1.4148013333333338,
+            "min": 0.49916386666666673,
+            "max": 2.3100570000000005,
+            "count": 34
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0006936199814285716,
-            "min": 0.0006936199814285716,
-            "max": 0.007791950259999998,
-            "count": 13
+            "value": 0.00011561808571428563,
+            "min": 0.00011561808571428563,
+            "max": 0.00664215676,
+            "count": 34
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.009710679740000002,
-            "min": 0.009710679740000002,
-            "max": 0.08052927023999999,
-            "count": 13
+            "value": 0.0016186531999999988,
+            "min": 0.0016186531999999988,
+            "max": 0.0910546943,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.019538814201951027,
-            "min": 0.019538814201951027,
-            "max": 0.052870769053697586,
-            "count": 13
+            "value": 0.010202839970588684,
+            "min": 0.010060305707156658,
+            "max": 0.020084787160158157,
+            "count": 34
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.2735433876514435,
-            "min": 0.21148307621479034,
-            "max": 0.4636197090148926,
-            "count": 13
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 960.4193548387096,
-            "min": 877.969696969697,
-            "max": 999.0,
-            "count": 13
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29773.0,
-            "min": 15984.0,
-            "max": 32379.0,
-            "count": 13
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.6382710169399938,
-            "min": -1.0000000521540642,
-            "max": -0.2531588686739697,
-            "count": 13
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -19.78640152513981,
-            "min": -27.998801454901695,
-            "max": -8.60740153491497,
-            "count": 13
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.6382710169399938,
-            "min": -1.0000000521540642,
-            "max": -0.2531588686739697,
-            "count": 13
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -19.78640152513981,
-            "min": -27.998801454901695,
-            "max": -8.60740153491497,
-            "count": 13
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.1995494886031074,
-            "min": 0.18775655897898655,
-            "max": 0.5538524850271642,
-            "count": 13
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 6.186034146696329,
-            "min": 6.186034146696329,
-            "max": 14.748457720503211,
-            "count": 13
+            "value": 0.14283975958824158,
+            "min": 0.05922834575176239,
+            "max": 0.2811870276927948,
+            "count": 34
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 13
+            "count": 34
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 13
+            "count": 34
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679880702",
+        "start_time_seconds": "1679882068",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679881857"
+        "end_time_seconds": "1679885401"
     },
-    "total": 1154.5431081349998,
+    "total": 3332.302809297,
     "count": 1,
-    "self": 0.5793679280000106,
+    "self": 0.5953055580002911,
     "children": {
         "run_training.setup": {
-            "total": 0.13834443599989754,
+            "total": 0.13212189299974852,
             "count": 1,
-            "self": 0.13834443599989754
+            "self": 0.13212189299974852
         },
         "TrainerController.start_learning": {
-            "total": 1153.8253957709999,
+            "total": 3331.575381846,
             "count": 1,
-            "self": 0.8401205500185824,
+            "self": 2.333438276002198,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.9046113479998894,
+                    "total": 5.435023740999895,
                     "count": 1,
-                    "self": 3.9046113479998894
+                    "self": 5.435023740999895
                 },
                 "TrainerController.advance": {
-                    "total": 1148.9817607849814,
-                    "count": 25262,
-                    "self": 0.99654881100696,
+                    "total": 3323.6996491129976,
+                    "count": 64337,
+                    "self": 2.5265376661873233,
                     "children": {
                         "env_step": {
-                            "total": 744.6364724559958,
-                            "count": 25262,
-                            "self": 691.1506517898792,
+                            "total": 2247.403280915897,
+                            "count": 64337,
+                            "self": 2114.6026447800486,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 52.95715865204102,
-                                    "count": 25262,
-                                    "self": 2.6429247589949227,
+                                    "total": 131.37163090778722,
+                                    "count": 64337,
+                                    "self": 6.562056770887466,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 50.314233893046094,
-                                            "count": 25028,
-                                            "self": 50.314233893046094
+                                            "total": 124.80957413689976,
+                                            "count": 62549,
+                                            "self": 124.80957413689976
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.5286620140755076,
-                                    "count": 25262,
+                                    "total": 1.4290052280612144,
+                                    "count": 64337,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1151.4027802629375,
-                                            "count": 25262,
+                                            "total": 3324.3106096400124,
+                                            "count": 64337,
                                             "is_parallel": true,
-                                            "self": 527.3528386969961,
+                                            "self": 1379.4548536519178,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021955069996693055,
+                                                            "total": 0.003024829999958456,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006880489991090144,
+                                                            "self": 0.0008231780002461164,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0015074580005602911,
+                                                                    "total": 0.0022016519997123396,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0015074580005602911
+                                                                    "self": 0.0022016519997123396
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06192197700011093,
+                                                            "total": 0.09306360099981248,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006188610000208428,
+                                                            "self": 0.0006208509994394262,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00031698700013294,
+                                                                    "total": 0.0005132300002514967,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00031698700013294
+                                                                    "self": 0.0005132300002514967
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0588842699999077,
+                                                                    "total": 0.08995682099975966,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0588842699999077
+                                                                    "self": 0.08995682099975966
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002101859000049444,
+                                                                    "total": 0.0019726990003618994,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004612339998857351,
+                                                                    "self": 0.00044938199971511494,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001640625000163709,
+                                                                            "total": 0.0015233170006467844,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001640625000163709
+                                                                            "self": 0.0015233170006467844
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 624.0499415659415,
-                                                    "count": 25261,
+                                                    "total": 1944.8557559880946,
+                                                    "count": 64336,
                                                     "is_parallel": true,
-                                                    "self": 16.59727313300391,
+                                                    "self": 42.58033807901211,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 10.078693548031424,
-                                                            "count": 25261,
+                                                            "total": 26.081649256087076,
+                                                            "count": 64336,
                                                             "is_parallel": true,
-                                                            "self": 10.078693548031424
+                                                            "self": 26.081649256087076
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 548.0638748069696,
-                                                            "count": 25261,
+                                                            "total": 1750.0566777308204,
+                                                            "count": 64336,
                                                             "is_parallel": true,
-                                                            "self": 548.0638748069696
+                                                            "self": 1750.0566777308204
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 49.31010007793657,
-                                                            "count": 25261,
+                                                            "total": 126.13709092217505,
+                                                            "count": 64336,
                                                             "is_parallel": true,
-                                                            "self": 10.908833783036698,
+                                                            "self": 28.810998218191344,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 38.40126629489987,
-                                                                    "count": 202088,
+                                                                    "total": 97.3260927039837,
+                                                                    "count": 514688,
                                                                     "is_parallel": true,
-                                                                    "self": 38.40126629489987
+                                                                    "self": 97.3260927039837
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 403.34873951797863,
-                            "count": 25262,
-                            "self": 1.6501944739552528,
+                            "total": 1073.7698305309132,
+                            "count": 64337,
+                            "self": 4.693636518783933,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 59.22780203302409,
-                                    "count": 25262,
-                                    "self": 59.09723188102453,
+                                    "total": 151.88804837512998,
+                                    "count": 64337,
+                                    "self": 151.66285565312955,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.13057015199956368,
-                                            "count": 1,
-                                            "self": 0.13057015199956368
+                                            "total": 0.22519272200042906,
+                                            "count": 2,
+                                            "self": 0.22519272200042906
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 342.4707430109993,
-                                    "count": 171,
-                                    "self": 150.53439868399755,
+                                    "total": 917.1881456369993,
+                                    "count": 470,
+                                    "self": 393.269350020998,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 191.93634432700173,
-                                            "count": 9099,
-                                            "self": 191.93634432700173
+                                            "total": 523.9187956160013,
+                                            "count": 22740,
+                                            "self": 523.9187956160013
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2900000001536682e-06,
+                    "total": 1.1020001693395898e-06,
                     "count": 1,
-                    "self": 1.2900000001536682e-06
+                    "self": 1.1020001693395898e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09890179800004262,
+                    "total": 0.10726961399996071,
                     "count": 1,
-                    "self": 0.0024370920000365004,
+                    "self": 0.0024033519985096063,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09646470600000612,
+                            "total": 0.1048662620014511,
                             "count": 1,
-                            "self": 0.09646470600000612
+                            "self": 0.1048662620014511
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 40192,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-40192.onnx",
-                "reward": null,
-                "creation_time": 1679880200.2180147,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-40192.pt"
-                ]
-            },
-            {
-                "steps": 100369,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-100369.onnx",
-                "reward": null,
-                "creation_time": 1679880568.8058193,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-100369.pt"
-                ]
-            },
             {
                 "steps": 499931,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-499931.onnx",
@@ -36,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-500035.pt"
                 ]
+            },
+            {
+                "steps": 999901,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999901.onnx",
+                "reward": 1.6262856743165426,
+                "creation_time": 1679883663.2884867,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999901.pt"
+                ]
+            },
+            {
+                "steps": 1499928,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499928.onnx",
+                "reward": 1.764777758055263,
+                "creation_time": 1679885400.4569874,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499928.pt"
+                ]
+            },
+            {
+                "steps": 1500056,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500056.onnx",
+                "reward": 1.764777758055263,
+                "creation_time": 1679885400.5781524,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500056.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500035,
+            "steps": 1500056,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": -0.9994000494480133,
-            "creation_time": 1679881856.6793034,
+            "reward": 1.764777758055263,
+            "creation_time": 1679885400.5781524,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500035.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1500056.pt"
             ]
         }
     },