First Commit

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27546e534101f556b8705dde1d8ed44305895d2fccb79c7bf9f21449fdc8772
+oid sha256:ab76005576dc0e64a54f4b8c62c7df03638017b0e2791bf2a24ca764a80bdb9d
 size 1418184

Pyramids/Pyramids-499931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab76005576dc0e64a54f4b8c62c7df03638017b0e2791bf2a24ca764a80bdb9d
+size 1418184

Pyramids/Pyramids-499931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea5f7013c0e0c5b0f7993c4af136b2fee1f2a34096f488412997965f99589108
+size 8650158

Pyramids/Pyramids-500035.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab76005576dc0e64a54f4b8c62c7df03638017b0e2791bf2a24ca764a80bdb9d
+size 1418184

Pyramids/Pyramids-500035.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:801a1335cb0da12fbaeb1edf2cd50f76de5c9b5dd91dba45205205e795f77e8f
+size 8650158

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104cc77065e9d5a34eeb67190ad237384fbf0632a784cb117518b5d22f99cd19
+oid sha256:801a1335cb0da12fbaeb1edf2cd50f76de5c9b5dd91dba45205205e795f77e8f
 size 8650158

Pyramids/events.out.tfevents.1679880706.3bb84cbeccac.15815.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ac9fb1cbc998446adbe57fae21c96e1685a8e541ad9b8236562bd25963356c
+size 116729

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": 100000, "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": 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}

configuration.yaml

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 100000
+    max_steps: 500000
     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] 55283 [Flags] 2 [Guid] 3429199380 [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] 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]...
 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  0.138 seconds
+- Completed reload, in  0.114 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: 1.346924 ms
+UnloadTime: 1.081347 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]: 643 frames, [32.0 KB-64.0 KB]: 447 frames, [64.0 KB-128.0 KB]: 40 frames, [2.0 MB-4.0 MB]: 1 frames
+      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
       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 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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]: 832 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 7210 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12451
+  Peak main deferred allocation count 11550
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1130 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 7508 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.5 MB
+      Peak Allocated memory 31.9 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1131 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 7509 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.8 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -254,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1130 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7508 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]: 1131 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 7509 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -272,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 832 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 7210 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]: 1130 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 7508 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
@@ -290,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1131 frames
+      Peak usage frame count: [0-1.0 KB]: 7509 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]: 1131 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 7509 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]: 1131 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 7509 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 27.4 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1679880569336,"processId":14339,"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":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}]}

run_logs/timers.json

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 1.1319851875305176,
-            "min": 1.1319851875305176,
-            "max": 1.2139133214950562,
-            "count": 2
+            "value": 0.6851799488067627,
+            "min": 0.6851799488067627,
+            "max": 1.0732108354568481,
+            "count": 13
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 33905.21875,
-            "min": 24394.802734375,
-            "max": 33905.21875,
-            "count": 2
+            "value": 20665.02734375,
+            "min": 20665.02734375,
+            "max": 30553.39453125,
+            "count": 13
         },
         "Pyramids.Step.mean": {
-            "value": 89897.0,
-            "min": 59904.0,
-            "max": 89897.0,
-            "count": 2
+            "value": 479973.0,
+            "min": 119953.0,
+            "max": 479973.0,
+            "count": 13
         },
         "Pyramids.Step.sum": {
-            "value": 89897.0,
-            "min": 59904.0,
-            "max": 89897.0,
-            "count": 2
+            "value": 479973.0,
+            "min": 119953.0,
+            "max": 479973.0,
+            "count": 13
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.09074477106332779,
-            "min": -0.09215711057186127,
-            "max": -0.09074477106332779,
-            "count": 2
+            "value": -0.04727970436215401,
+            "min": -0.09163922071456909,
+            "max": -0.018209222704172134,
+            "count": 13
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -21.869489669799805,
-            "min": -21.869489669799805,
-            "max": -14.468666076660156,
-            "count": 2
+            "value": -11.441688537597656,
+            "min": -21.90177345275879,
+            "max": -4.461259365081787,
+            "count": 13
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.1566082388162613,
-            "min": 0.1566082388162613,
-            "max": 0.22529001533985138,
-            "count": 2
+            "value": 0.02514275163412094,
+            "min": 0.019109051674604416,
+            "max": 0.084037646651268,
+            "count": 13
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 37.742584228515625,
-            "min": 35.37053298950195,
-            "max": 37.742584228515625,
-            "count": 2
+            "value": 6.084546089172363,
+            "min": 4.624390602111816,
+            "max": 14.788856506347656,
+            "count": 13
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0671909608450867,
-            "min": 0.06697793670817233,
-            "max": 0.0671909608450867,
-            "count": 2
+            "value": 0.06645620250728775,
+            "min": 0.06553690842359469,
+            "max": 0.07159876862969432,
+            "count": 13
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.5375276867606936,
-            "min": 0.2679117468326893,
-            "max": 0.5375276867606936,
-            "count": 2
+            "value": 0.9303868351020284,
+            "min": 0.265779438362679,
+            "max": 1.047773662234249,
+            "count": 13
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.0009453999675119055,
-            "min": 0.0009453999675119055,
-            "max": 0.0010875157755362616,
-            "count": 2
+            "value": 0.002682014867945663,
+            "min": 0.00020303111836860016,
+            "max": 0.005888134813581385,
+            "count": 13
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.007563199740095244,
-            "min": 0.004350063102145046,
-            "max": 0.007563199740095244,
-            "count": 2
+            "value": 0.037548208151239285,
+            "min": 0.002436373420423202,
+            "max": 0.07422052906208682,
+            "count": 13
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.841932386025e-05,
-            "min": 7.841932386025e-05,
-            "max": 0.00014899205033600002,
-            "count": 2
+            "value": 2.052922172838571e-05,
+            "min": 2.052922172838571e-05,
+            "max": 0.0002336922221026,
+            "count": 13
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.000627354590882,
-            "min": 0.0005959682013440001,
-            "max": 0.000627354590882,
-            "count": 2
+            "value": 0.0002874091041973999,
+            "min": 0.0002874091041973999,
+            "max": 0.0024146931951024003,
+            "count": 13
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.12613975,
-            "min": 0.12613975,
-            "max": 0.14966400000000002,
-            "count": 2
+            "value": 0.10684304285714284,
+            "min": 0.10684304285714284,
+            "max": 0.1778974,
+            "count": 13
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.009118,
-            "min": 0.5986560000000001,
-            "max": 1.009118,
-            "count": 2
+            "value": 1.4958025999999998,
+            "min": 0.7115896,
+            "max": 2.013959,
+            "count": 13
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0026213610250000003,
-            "min": 0.0026213610250000003,
-            "max": 0.0049714336,
-            "count": 2
+            "value": 0.0006936199814285716,
+            "min": 0.0006936199814285716,
+            "max": 0.007791950259999998,
+            "count": 13
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.020970888200000003,
-            "min": 0.0198857344,
-            "max": 0.020970888200000003,
-            "count": 2
+            "value": 0.009710679740000002,
+            "min": 0.009710679740000002,
+            "max": 0.08052927023999999,
+            "count": 13
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.0843014270067215,
-            "min": 0.0843014270067215,
-            "max": 0.1316838562488556,
-            "count": 2
+            "value": 0.019538814201951027,
+            "min": 0.019538814201951027,
+            "max": 0.052870769053697586,
+            "count": 13
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.674411416053772,
-            "min": 0.5267354249954224,
-            "max": 0.674411416053772,
-            "count": 2
+            "value": 0.2735433876514435,
+            "min": 0.21148307621479034,
+            "max": 0.4636197090148926,
+            "count": 13
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 984.28125,
-            "min": 984.28125,
+            "value": 960.4193548387096,
+            "min": 877.969696969697,
             "max": 999.0,
-            "count": 2
+            "count": 13
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31497.0,
+            "value": 29773.0,
             "min": 15984.0,
-            "max": 31497.0,
-            "count": 2
+            "max": 32379.0,
+            "count": 13
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.9227500522974879,
+            "value": -0.6382710169399938,
             "min": -1.0000000521540642,
-            "max": -0.9227500522974879,
-            "count": 2
+            "max": -0.2531588686739697,
+            "count": 13
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -29.52800167351961,
-            "min": -29.52800167351961,
-            "max": -16.000000834465027,
-            "count": 2
+            "value": -19.78640152513981,
+            "min": -27.998801454901695,
+            "max": -8.60740153491497,
+            "count": 13
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.9227500522974879,
+            "value": -0.6382710169399938,
             "min": -1.0000000521540642,
-            "max": -0.9227500522974879,
-            "count": 2
+            "max": -0.2531588686739697,
+            "count": 13
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -29.52800167351961,
-            "min": -29.52800167351961,
-            "max": -16.000000834465027,
-            "count": 2
+            "value": -19.78640152513981,
+            "min": -27.998801454901695,
+            "max": -8.60740153491497,
+            "count": 13
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.8801894574426115,
-            "min": 0.8801894574426115,
-            "max": 1.438847019802779,
-            "count": 2
+            "value": 0.1995494886031074,
+            "min": 0.18775655897898655,
+            "max": 0.5538524850271642,
+            "count": 13
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 28.166062638163567,
-            "min": 23.021552316844463,
-            "max": 28.166062638163567,
-            "count": 2
+            "value": 6.186034146696329,
+            "min": 6.186034146696329,
+            "max": 14.748457720503211,
+            "count": 13
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 13
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 2
+            "count": 13
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679880401",
+        "start_time_seconds": "1679880702",
         "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": "1679880569"
+        "end_time_seconds": "1679881857"
     },
-    "total": 167.93068290699966,
+    "total": 1154.5431081349998,
     "count": 1,
-    "self": 0.5801030379998338,
+    "self": 0.5793679280000106,
     "children": {
         "run_training.setup": {
-            "total": 0.1345584969999436,
+            "total": 0.13834443599989754,
             "count": 1,
-            "self": 0.1345584969999436
+            "self": 0.13834443599989754
         },
         "TrainerController.start_learning": {
-            "total": 167.2160213719999,
+            "total": 1153.8253957709999,
             "count": 1,
-            "self": 0.1191511889951471,
+            "self": 0.8401205500185824,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.035895902999982,
+                    "total": 3.9046113479998894,
                     "count": 1,
-                    "self": 5.035895902999982
+                    "self": 3.9046113479998894
                 },
                 "TrainerController.advance": {
-                    "total": 161.9355113670049,
-                    "count": 3770,
-                    "self": 0.14578705200938202,
+                    "total": 1148.9817607849814,
+                    "count": 25262,
+                    "self": 0.99654881100696,
                     "children": {
                         "env_step": {
-                            "total": 100.22510789899479,
-                            "count": 3770,
-                            "self": 91.81223150700043,
+                            "total": 744.6364724559958,
+                            "count": 25262,
+                            "self": 691.1506517898792,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 8.334210197988796,
-                                    "count": 3770,
-                                    "self": 0.3967263059907964,
+                                    "total": 52.95715865204102,
+                                    "count": 25262,
+                                    "self": 2.6429247589949227,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 7.937483891997999,
-                                            "count": 3768,
-                                            "self": 7.937483891997999
+                                            "total": 50.314233893046094,
+                                            "count": 25028,
+                                            "self": 50.314233893046094
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.07866619400556374,
-                                    "count": 3770,
+                                    "total": 0.5286620140755076,
+                                    "count": 25262,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 166.5124674120043,
-                                            "count": 3770,
+                                            "total": 1151.4027802629375,
+                                            "count": 25262,
                                             "is_parallel": true,
-                                            "self": 84.14824784902203,
+                                            "self": 527.3528386969961,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.003092433999881905,
+                                                            "total": 0.0021955069996693055,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0010172100001000217,
+                                                            "self": 0.0006880489991090144,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0020752239997818833,
+                                                                    "total": 0.0015074580005602911,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0020752239997818833
+                                                                    "self": 0.0015074580005602911
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.12078330899976208,
+                                                            "total": 0.06192197700011093,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006206919997566729,
+                                                            "self": 0.0006188610000208428,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.000536837999788986,
+                                                                    "total": 0.00031698700013294,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000536837999788986
+                                                                    "self": 0.00031698700013294
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.11772171100028572,
+                                                                    "total": 0.0588842699999077,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.11772171100028572
+                                                                    "self": 0.0588842699999077
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001904067999930703,
+                                                                    "total": 0.002101859000049444,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004236190006849938,
+                                                                    "self": 0.0004612339998857351,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014804489992457093,
+                                                                            "total": 0.001640625000163709,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014804489992457093
+                                                                            "self": 0.001640625000163709
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 82.36421956298227,
-                                                    "count": 3769,
+                                                    "total": 624.0499415659415,
+                                                    "count": 25261,
                                                     "is_parallel": true,
-                                                    "self": 2.4686994339717785,
+                                                    "self": 16.59727313300391,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 1.4832412849978027,
-                                                            "count": 3769,
+                                                            "total": 10.078693548031424,
+                                                            "count": 25261,
                                                             "is_parallel": true,
-                                                            "self": 1.4832412849978027
+                                                            "self": 10.078693548031424
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 71.03489979100277,
-                                                            "count": 3769,
+                                                            "total": 548.0638748069696,
+                                                            "count": 25261,
                                                             "is_parallel": true,
-                                                            "self": 71.03489979100277
+                                                            "self": 548.0638748069696
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 7.377379053009918,
-                                                            "count": 3769,
+                                                            "total": 49.31010007793657,
+                                                            "count": 25261,
                                                             "is_parallel": true,
-                                                            "self": 1.6965565460100152,
+                                                            "self": 10.908833783036698,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 5.6808225069999025,
-                                                                    "count": 30152,
+                                                                    "total": 38.40126629489987,
+                                                                    "count": 202088,
                                                                     "is_parallel": true,
-                                                                    "self": 5.6808225069999025
+                                                                    "self": 38.40126629489987
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 61.56461641600072,
-                            "count": 3770,
-                            "self": 0.17372190000787668,
+                            "total": 403.34873951797863,
+                            "count": 25262,
+                            "self": 1.6501944739552528,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 8.777848308992816,
-                                    "count": 3770,
-                                    "self": 8.777848308992816
+                                    "total": 59.22780203302409,
+                                    "count": 25262,
+                                    "self": 59.09723188102453,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.13057015199956368,
+                                            "count": 1,
+                                            "self": 0.13057015199956368
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 52.613046207000025,
-                                    "count": 16,
-                                    "self": 23.32516488500778,
+                                    "total": 342.4707430109993,
+                                    "count": 171,
+                                    "self": 150.53439868399755,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 29.287881321992245,
-                                            "count": 1362,
-                                            "self": 29.287881321992245
+                                            "total": 191.93634432700173,
+                                            "count": 9099,
+                                            "self": 191.93634432700173
                                         }
                                     }
                                 }
@@ -369,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1679999261104967e-06,
+                    "total": 1.2900000001536682e-06,
                     "count": 1,
-                    "self": 1.1679999261104967e-06
+                    "self": 1.2900000001536682e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12546174499993867,
+                    "total": 0.09890179800004262,
                     "count": 1,
-                    "self": 0.0031917869996505033,
+                    "self": 0.0024370920000365004,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12226995800028817,
+                            "total": 0.09646470600000612,
                             "count": 1,
-                            "self": 0.12226995800028817
+                            "self": 0.09646470600000612
                         }
                     }
                 }

run_logs/training_status.json

@@ -18,15 +18,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-100369.pt"
                 ]
+            },
+            {
+                "steps": 499931,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499931.onnx",
+                "reward": -0.9995000511407852,
+                "creation_time": 1679881856.5711381,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499931.pt"
+                ]
+            },
+            {
+                "steps": 500035,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500035.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1679881856.6793034,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-500035.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 100369,
+            "steps": 500035,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1679880568.8058193,
+            "reward": -0.9994000494480133,
+            "creation_time": 1679881856.6793034,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-100369.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-500035.pt"
             ]
         }
     },