pushed the model

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584085e0f48ab6be2bc16cbcd15eed32916c2ed252f672c61222c21bab390851
+oid sha256:d8ef1135726369f57ad0fa5ecca8b028b1c53fb37bbd6248f3cd3f229ad46124
 size 1418184

Pyramids/Pyramids-1250051.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ef1135726369f57ad0fa5ecca8b028b1c53fb37bbd6248f3cd3f229ad46124
+size 1418184

Pyramids/Pyramids-1250051.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fa1531899e24c582d31ad9ffd9dabb5836fb7ce9c0f49c20bb23aa1c3b1a50
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9477b174723d140b423de6cccb2709e8da00b694869c6c94c7ef141049877498
+oid sha256:93fa1531899e24c582d31ad9ffd9dabb5836fb7ce9c0f49c20bb23aa1c3b1a50
 size 8650990

Pyramids/events.out.tfevents.1694052164.f5001fcc51d4.25030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b811efea9eafc95542b951647329defcf728cbf68ed12adcb5b36852706212d
+size 8446

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": 0.05, "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": 1240000, "time_horizon": 128, "summary_freq": 1000, "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": 0.01, "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": 1250000, "time_horizon": 128, "summary_freq": 1000, "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

@@ -7,7 +7,7 @@ behaviors:
       buffer_size: 2048
       learning_rate: 0.0003
       beta: 0.01
-      epsilon: 0.05
+      epsilon: 0.01
       lambd: 0.95
       num_epoch: 3
       shared_critic: false
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1240000
+    max_steps: 1250000
     time_horizon: 128
     summary_freq: 1000
     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] 55319 [Flags] 2 [Guid] 774953189 [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] 55322 [Flags] 2 [Guid] 2911863996 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.093 seconds
+- Completed reload, in  0.105 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -65,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.893321 ms
+UnloadTime: 1.017239 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]: 3 frames, [32.0 KB-64.0 KB]: 137 frames, [64.0 KB-128.0 KB]: 62 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4 frames, [32.0 KB-64.0 KB]: 137 frames, [64.0 KB-128.0 KB]: 66 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
@@ -183,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       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]: 26 frames, [1.0 MB-2.0 MB]: 177 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 32 frames, [1.0 MB-2.0 MB]: 176 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
   Peak Allocated memory 1.0 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12695
+  Peak main deferred allocation count 10899
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 202 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 2 frames, [16.0 MB-32.0 MB]: 206 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 21.3 MB
+      Peak Allocated memory 21.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 203 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 208 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 22.3 MB
+      Peak Allocated memory 24.1 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 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 202 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 207 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]: 203 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 208 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 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 48 frames, [1.0 MB-2.0 MB]: 155 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 42 frames, [1.0 MB-2.0 MB]: 166 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 1.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 202 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 207 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
@@ -290,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 203 frames
+      Peak usage frame count: [0-1.0 KB]: 208 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]: 203 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 208 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]: 203 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 208 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 27.4 KB
@@ -311,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1694052157394,"processId":24804,"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":1694052202187,"processId":25046,"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

@@ -2,99 +2,99 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.370998352766037,
-            "min": 0.3300286829471588,
-            "max": 0.40049487352371216,
+            "value": 0.3516780436038971,
+            "min": 0.3516780436038971,
+            "max": 0.41696587204933167,
             "count": 9
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 290.8627014160156,
-            "min": 238.03443908691406,
-            "max": 804.9423828125,
+            "value": 388.2525634765625,
+            "min": 218.91485595703125,
+            "max": 768.5119018554688,
             "count": 9
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 166.0,
-            "min": 102.0,
-            "max": 352.8,
+            "value": 182.0,
+            "min": 113.0,
+            "max": 308.5,
             "count": 9
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 166.0,
-            "min": 166.0,
-            "max": 1764.0,
+            "value": 546.0,
+            "min": 339.0,
+            "max": 1671.0,
             "count": 9
         },
         "Pyramids.Step.mean": {
-            "value": 1239936.0,
-            "min": 1230989.0,
-            "max": 1239936.0,
+            "value": 1249962.0,
+            "min": 1240918.0,
+            "max": 1249962.0,
             "count": 10
         },
         "Pyramids.Step.sum": {
-            "value": 1239936.0,
-            "min": 1230989.0,
-            "max": 1239936.0,
+            "value": 1249962.0,
+            "min": 1240918.0,
+            "max": 1249962.0,
             "count": 10
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3248412609100342,
-            "min": 0.3248412609100342,
-            "max": 0.8336101174354553,
+            "value": 0.4971886873245239,
+            "min": 0.2919323742389679,
+            "max": 0.8410938382148743,
             "count": 10
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 2.9235713481903076,
-            "min": 2.4123728275299072,
-            "max": 9.169711112976074,
+            "value": 3.9775094985961914,
+            "min": 2.335458993911743,
+            "max": 9.252032279968262,
             "count": 10
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.19955527782440186,
-            "min": 0.19955527782440186,
-            "max": 0.5185986161231995,
+            "value": 0.2859998941421509,
+            "min": 0.18785905838012695,
+            "max": 0.45955944061279297,
             "count": 10
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 1.7959975004196167,
-            "min": 1.6263935565948486,
-            "max": 5.70458459854126,
+            "value": 2.287999153137207,
+            "min": 1.5028724670410156,
+            "max": 5.055153846740723,
             "count": 10
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.8340000063180923,
-            "min": 1.5904999822378159,
-            "max": 1.8979999423027039,
+            "value": 1.8349999859929085,
+            "min": 1.6459999829530716,
+            "max": 1.8869999647140503,
             "count": 9
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 1.8340000063180923,
-            "min": 1.7290000021457672,
-            "max": 12.761000007390976,
+            "value": 3.669999971985817,
+            "min": 3.4309999346733093,
+            "max": 12.605999812483788,
             "count": 9
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.8340000063180923,
-            "min": 1.5904999822378159,
-            "max": 1.8979999423027039,
+            "value": 1.8349999859929085,
+            "min": 1.6459999829530716,
+            "max": 1.8869999647140503,
             "count": 9
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 1.8340000063180923,
-            "min": 1.7290000021457672,
-            "max": 12.761000007390976,
+            "value": 3.669999971985817,
+            "min": 3.4309999346733093,
+            "max": 12.605999812483788,
             "count": 9
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.013750533806160092,
-            "min": 0.010786477010697126,
-            "max": 0.03329771873541176,
+            "value": 0.012570885941386223,
+            "min": 0.010363222332671285,
+            "max": 0.035048372383850314,
             "count": 9
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 0.013750533806160092,
-            "min": 0.013750533806160092,
-            "max": 0.14000716526061296,
+            "value": 0.025141771882772446,
+            "min": 0.025141771882772446,
+            "max": 0.12838379037566483,
             "count": 9
         },
         "Pyramids.IsTraining.mean": {
@@ -110,81 +110,81 @@
             "count": 10
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06123122064551959,
-            "min": 0.06123122064551959,
-            "max": 0.07143721706233919,
+            "value": 0.0693604327000988,
+            "min": 0.06358630953279014,
+            "max": 0.0693604327000988,
             "count": 4
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.06123122064551959,
-            "min": 0.06123122064551959,
-            "max": 0.07143721706233919,
+            "value": 0.0693604327000988,
+            "min": 0.06358630953279014,
+            "max": 0.0693604327000988,
             "count": 4
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.03391708111545692,
-            "min": 0.017989460417690378,
-            "max": 0.03391708111545692,
+            "value": 0.027095112949609756,
+            "min": 0.014626392046920955,
+            "max": 0.027095112949609756,
             "count": 4
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.03391708111545692,
-            "min": 0.017989460417690378,
-            "max": 0.03391708111545692,
+            "value": 0.027095112949609756,
+            "min": 0.014626392046920955,
+            "max": 0.027095112949609756,
             "count": 4
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 3.656643942741968e-07,
-            "min": 3.656643942741968e-07,
-            "max": 1.913083233306442e-06,
+            "value": 3.8697987104000055e-07,
+            "min": 3.8697987104000055e-07,
+            "max": 1.8903393699199986e-06,
             "count": 4
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 3.656643942741968e-07,
-            "min": 3.656643942741968e-07,
-            "max": 1.913083233306442e-06,
+            "value": 3.8697987104000055e-07,
+            "min": 3.8697987104000055e-07,
+            "max": 1.8903393699199986e-06,
             "count": 4
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.09993907258064516,
-            "min": 0.09968116935483871,
-            "max": 0.09993907258064516,
+            "value": 0.099883936,
+            "min": 0.09943292800000002,
+            "max": 0.099883936,
             "count": 4
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.09993907258064516,
-            "min": 0.09968116935483871,
-            "max": 0.09993907258064516,
+            "value": 0.099883936,
+            "min": 0.09943292800000002,
+            "max": 0.099883936,
             "count": 4
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 2.2173298387096884e-05,
-            "min": 2.2173298387096884e-05,
-            "max": 7.37023629032255e-05,
+            "value": 2.2883104000000022e-05,
+            "min": 2.2883104000000022e-05,
+            "max": 7.294499199999995e-05,
             "count": 4
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 2.2173298387096884e-05,
-            "min": 2.2173298387096884e-05,
-            "max": 7.37023629032255e-05,
+            "value": 2.2883104000000022e-05,
+            "min": 2.2883104000000022e-05,
+            "max": 7.294499199999995e-05,
             "count": 4
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007816636003553867,
-            "min": 0.007656558882445097,
-            "max": 0.008237515576183796,
+            "value": 0.008464193902909756,
+            "min": 0.008013986982405186,
+            "max": 0.008466011844575405,
             "count": 4
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.007816636003553867,
-            "min": 0.007656558882445097,
-            "max": 0.008237515576183796,
+            "value": 0.008464193902909756,
+            "min": 0.008013986982405186,
+            "max": 0.008466011844575405,
             "count": 4
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1694052121",
+        "start_time_seconds": "1694052163",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "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": "1694052157"
+        "end_time_seconds": "1694052202"
     },
-    "total": 36.31466854199971,
+    "total": 38.40765666599964,
     "count": 1,
-    "self": 0.5267161020001367,
+    "self": 0.5276233879994834,
     "children": {
         "run_training.setup": {
-            "total": 0.04789883400007966,
+            "total": 0.046680598000421014,
             "count": 1,
-            "self": 0.04789883400007966
+            "self": 0.046680598000421014
         },
         "TrainerController.start_learning": {
-            "total": 35.74005360599949,
+            "total": 37.833352679999734,
             "count": 1,
-            "self": 0.021197826007664844,
+            "self": 0.021710760991481948,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 6.102413535999403,
+                    "total": 4.4256686899998385,
                     "count": 1,
-                    "self": 6.102413535999403
+                    "self": 4.4256686899998385
                 },
                 "TrainerController.advance": {
-                    "total": 29.501782374992217,
-                    "count": 699,
-                    "self": 0.0213413319997926,
+                    "total": 33.26726093100751,
+                    "count": 721,
+                    "self": 0.02136674400571792,
                     "children": {
                         "env_step": {
-                            "total": 23.36824196800626,
-                            "count": 699,
-                            "self": 21.893842020002012,
+                            "total": 26.44817369300108,
+                            "count": 721,
+                            "self": 24.932001471974218,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1.4631497079953988,
-                                    "count": 699,
-                                    "self": 0.06574880898824631,
+                                    "total": 1.5037104810098754,
+                                    "count": 721,
+                                    "self": 0.06397840400586574,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1.3974008990071525,
-                                            "count": 675,
-                                            "self": 1.3974008990071525
+                                            "total": 1.4397320770040096,
+                                            "count": 691,
+                                            "self": 1.4397320770040096
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.011250240008848778,
-                                    "count": 699,
+                                    "total": 0.012461740016988188,
+                                    "count": 721,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 35.59330222801327,
-                                            "count": 699,
+                                            "total": 37.63829906099545,
+                                            "count": 721,
                                             "is_parallel": true,
-                                            "self": 15.387539837999611,
+                                            "self": 14.398159981010394,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002777015999527066,
+                                                            "total": 0.0018329659997107228,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007460319984602393,
+                                                            "self": 0.0005873839972991846,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0020309840010668267,
+                                                                    "total": 0.0012455820024115383,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0020309840010668267
+                                                                    "self": 0.0012455820024115383
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.097991106000336,
+                                                            "total": 0.05722300700017513,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.005511294000825728,
+                                                            "self": 0.000664567000058014,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005410260000644485,
+                                                                    "total": 0.0005314509999152506,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005410260000644485
+                                                                    "self": 0.0005314509999152506
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.08979092099980335,
+                                                                    "total": 0.05380490900006407,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.08979092099980335
+                                                                    "self": 0.05380490900006407
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0021478649996424792,
+                                                                    "total": 0.002222080000137794,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00041171200064127333,
+                                                                    "self": 0.0004230700014886679,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001736152999001206,
+                                                                            "total": 0.001799009998649126,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001736152999001206
+                                                                            "self": 0.001799009998649126
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 20.20576239001366,
-                                                    "count": 698,
+                                                    "total": 23.240139079985056,
+                                                    "count": 720,
                                                     "is_parallel": true,
-                                                    "self": 0.4365732290198139,
+                                                    "self": 0.460737724005412,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.2871582470042995,
-                                                            "count": 698,
+                                                            "total": 0.2874121279883184,
+                                                            "count": 720,
                                                             "is_parallel": true,
-                                                            "self": 0.2871582470042995
+                                                            "self": 0.2874121279883184
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 18.132081517990628,
-                                                            "count": 698,
+                                                            "total": 21.09707925499606,
+                                                            "count": 720,
                                                             "is_parallel": true,
-                                                            "self": 18.132081517990628
+                                                            "self": 21.09707925499606
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 1.3499493959989195,
-                                                            "count": 698,
+                                                            "total": 1.394909972995265,
+                                                            "count": 720,
                                                             "is_parallel": true,
-                                                            "self": 0.2872890190246835,
+                                                            "self": 0.2882891400395238,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.062660376974236,
-                                                                    "count": 5584,
+                                                                    "total": 1.1066208329557412,
+                                                                    "count": 5760,
                                                                     "is_parallel": true,
-                                                                    "self": 1.062660376974236
+                                                                    "self": 1.1066208329557412
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 6.112199074986165,
-                            "count": 699,
-                            "self": 0.030852644984406652,
+                            "total": 6.797720494000714,
+                            "count": 721,
+                            "self": 0.03401165701143327,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 1.19813583800169,
-                                    "count": 699,
-                                    "self": 1.19813583800169
+                                    "total": 1.368775032990925,
+                                    "count": 721,
+                                    "self": 1.368775032990925
                                 },
                                 "_update_policy": {
-                                    "total": 4.883210592000069,
+                                    "total": 5.394933803998356,
                                     "count": 4,
-                                    "self": 3.171833289006827,
+                                    "self": 3.4573090049989332,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 1.7113773029932418,
+                                            "total": 1.9376247989994226,
                                             "count": 192,
-                                            "self": 1.7113773029932418
+                                            "self": 1.9376247989994226
                                         }
                                     }
                                 }
@@ -369,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.180999788630288e-06,
+                    "total": 1.356000211671926e-06,
                     "count": 1,
-                    "self": 1.180999788630288e-06
+                    "self": 1.356000211671926e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1146586880004179,
+                    "total": 0.1187109420006891,
                     "count": 1,
-                    "self": 0.0017767540011845995,
+                    "self": 0.0018677450007089647,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1128819339992333,
+                            "total": 0.11684319699998014,
                             "count": 1,
-                            "self": 0.1128819339992333
+                            "self": 0.11684319699998014
                         }
                     }
                 }

run_logs/training_status.json

@@ -6,15 +6,6 @@
     },
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 1200040,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200040.onnx",
-                "reward": null,
-                "creation_time": 1694051935.8271642,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1200040.pt"
-                ]
-            },
             {
                 "steps": 1200040,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200040.onnx",
@@ -50,15 +41,24 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1240064.pt"
                 ]
+            },
+            {
+                "steps": 1250051,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1250051.onnx",
+                "reward": 1.8304999768733978,
+                "creation_time": 1694052201.7304368,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1250051.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1240064,
+            "steps": 1250051,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.8340000063180923,
-            "creation_time": 1694052156.9286487,
+            "reward": 1.8304999768733978,
+            "creation_time": 1694052201.7304368,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1240064.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1250051.pt"
             ]
         }
     }