pushed the model

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40f29845d1c5b9aa33602d17a1364eceb1b19aa048cb074e8fac65ea8ee818e
+oid sha256:22675a39966c06322288cbf01d17aa641b0046e3bc0e32ce5355333a40244437
 size 1418184

Pyramids/Pyramids-1220046.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22675a39966c06322288cbf01d17aa641b0046e3bc0e32ce5355333a40244437
+size 1418184

Pyramids/Pyramids-1220046.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddc10d3b1dbc60f759a97e9f4fef2f92614d0603419e9a129654b366035b1360
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fcc47a4494ab23e71b604f1d388325a37e679737cfac82a31afe3ab1d67c35c
+oid sha256:ddc10d3b1dbc60f759a97e9f4fef2f92614d0603419e9a129654b366035b1360
 size 8650990

Pyramids/events.out.tfevents.1694051966.f5001fcc51d4.23933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:338d64676add7cfa6a40e8da132bdc17cbe24256dbac87138dfec14bd0fffbd7
+size 1423

Pyramids/events.out.tfevents.1694051996.f5001fcc51d4.24123.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a36c769593f2b7fdd4b54f3ed0e811362e044e3e96ea4c11f6b6177e03978b
+size 15856

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": 1200000, "time_horizon": 128, "summary_freq": 10000, "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": 0.15, "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": 1220000, "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: 0.2
+      epsilon: 0.15
       lambd: 0.95
       num_epoch: 3
       shared_critic: false
@@ -51,9 +51,9 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1200000
+    max_steps: 1220000
     time_horizon: 128
-    summary_freq: 10000
+    summary_freq: 1000
     threaded: false
     self_play: null
     behavioral_cloning: null

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] 55206 [Flags] 2 [Guid] 921134221 [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] 55109 [Flags] 2 [Guid] 2293160554 [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  0.100 seconds
+- Completed reload, in  0.097 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: 1.478202 ms
+UnloadTime: 0.918759 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]: 76 frames, [32.0 KB-64.0 KB]: 1277 frames, [64.0 KB-128.0 KB]: 538 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 10 frames, [32.0 KB-64.0 KB]: 278 frames, [64.0 KB-128.0 KB]: 105 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
@@ -123,7 +123,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -133,7 +133,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 2]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       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 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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]: 34 frames, [1.0 MB-2.0 MB]: 1858 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 36 frames, [1.0 MB-2.0 MB]: 358 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.1 MB
+  Peak Allocated memory 1.0 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 8487
+  Peak main deferred allocation count 12487
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      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]: 1891 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 393 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 21.3 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 1892 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 394 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.1 MB
+      Peak Allocated memory 23.2 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 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 1891 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 393 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]: 1892 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 394 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,39 +270,39 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 49 frames, [1.0 MB-2.0 MB]: 1843 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 68 frames, [1.0 MB-2.0 MB]: 326 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]: 1891 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 393 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.5 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.4 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 1892 frames
+      Peak usage frame count: [0-1.0 KB]: 394 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]: 1892 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 394 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]: 1892 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 394 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":1694051936723,"processId":22494,"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":1694052059136,"processId":24139,"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": 0.35400623083114624,
-            "min": 0.3287368416786194,
-            "max": 0.3809888958930969,
-            "count": 10
+            "value": 0.3675108551979065,
+            "min": 0.35634732246398926,
+            "max": 0.40985307097435,
+            "count": 19
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 3585.375,
-            "min": 3224.2509765625,
-            "max": 4053.856689453125,
-            "count": 10
+            "value": 382.2113037109375,
+            "min": 37.04850769042969,
+            "max": 772.878662109375,
+            "count": 19
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 254.27777777777777,
-            "min": 219.0,
-            "max": 377.1142857142857,
-            "count": 10
+            "value": 314.5,
+            "min": 99.0,
+            "max": 630.0,
+            "count": 18
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 9154.0,
-            "min": 7154.0,
-            "max": 13199.0,
-            "count": 10
+            "value": 629.0,
+            "min": 198.0,
+            "max": 2165.0,
+            "count": 18
         },
         "Pyramids.Step.mean": {
-            "value": 1199912.0,
-            "min": 1109887.0,
-            "max": 1199912.0,
-            "count": 10
+            "value": 1219918.0,
+            "min": 1200880.0,
+            "max": 1219918.0,
+            "count": 20
         },
         "Pyramids.Step.sum": {
-            "value": 1199912.0,
-            "min": 1109887.0,
-            "max": 1199912.0,
-            "count": 10
+            "value": 1219918.0,
+            "min": 1200880.0,
+            "max": 1219918.0,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.653383195400238,
-            "min": 0.5558645725250244,
-            "max": 0.653383195400238,
-            "count": 10
+            "value": 0.49945247173309326,
+            "min": 0.28273361921310425,
+            "max": 0.7534145712852478,
+            "count": 20
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 63.378170013427734,
-            "min": 50.027809143066406,
-            "max": 63.378170013427734,
-            "count": 10
+            "value": 4.495072364807129,
+            "min": 2.261868953704834,
+            "max": 8.096029281616211,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.5715085864067078,
-            "min": 0.4426353871822357,
-            "max": 0.8367797136306763,
-            "count": 10
+            "value": 0.34622785449028015,
+            "min": 0.25928956270217896,
+            "max": 0.6301274299621582,
+            "count": 20
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 55.43633270263672,
-            "min": 42.49299621582031,
-            "max": 80.0146484375,
-            "count": 10
+            "value": 3.1160507202148438,
+            "min": 2.0743165016174316,
+            "max": 6.457930088043213,
+            "count": 20
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.690144433743424,
-            "min": 1.3873705653583301,
-            "max": 1.7809999925749642,
-            "count": 10
+            "value": 1.6854999959468842,
+            "min": 1.3700000122189522,
+            "max": 1.9009999632835388,
+            "count": 18
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 60.84519961476326,
-            "min": 39.384799391031265,
-            "max": 64.4709991067648,
-            "count": 10
+            "value": 3.3709999918937683,
+            "min": 1.4929999560117722,
+            "max": 10.872999876737595,
+            "count": 18
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.690144433743424,
-            "min": 1.3873705653583301,
-            "max": 1.7809999925749642,
-            "count": 10
+            "value": 1.6854999959468842,
+            "min": 1.3700000122189522,
+            "max": 1.9009999632835388,
+            "count": 18
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 60.84519961476326,
-            "min": 39.384799391031265,
-            "max": 64.4709991067648,
-            "count": 10
+            "value": 3.3709999918937683,
+            "min": 1.4929999560117722,
+            "max": 10.872999876737595,
+            "count": 18
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.021356650632191707,
-            "min": 0.02083654456572341,
-            "max": 0.03267753588091903,
-            "count": 10
+            "value": 0.025721535552293062,
+            "min": 0.009421935770660639,
+            "max": 0.042126540560275316,
+            "count": 18
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 0.7688394227589015,
-            "min": 0.6474357877159491,
-            "max": 1.0256763279030565,
-            "count": 10
+            "value": 0.051443071104586124,
+            "min": 0.018843871541321278,
+            "max": 0.17348272213712335,
+            "count": 18
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07095266573596745,
-            "min": 0.06245497111134077,
-            "max": 0.07095266573596745,
-            "count": 10
+            "value": 0.05649530321049193,
+            "min": 0.05649530321049193,
+            "max": 0.07723655512866874,
+            "count": 9
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.3547633286798373,
-            "min": 0.24981988444536307,
-            "max": 0.3547633286798373,
-            "count": 10
+            "value": 0.05649530321049193,
+            "min": 0.05649530321049193,
+            "max": 0.07723655512866874,
+            "count": 9
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.028200244236116605,
-            "min": 0.0246676901782242,
-            "max": 0.0438803927701277,
-            "count": 10
+            "value": 0.012976016014969597,
+            "min": 0.012716310457714522,
+            "max": 0.027080372208729386,
+            "count": 9
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.14100122118058303,
-            "min": 0.12333845089112098,
-            "max": 0.2194019638506385,
-            "count": 10
+            "value": 0.012976016014969597,
+            "min": 0.012716310457714522,
+            "max": 0.027080372208729386,
+            "count": 9
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 1.2104495965500022e-06,
-            "min": 1.2104495965500022e-06,
-            "max": 2.3687092104333334e-05,
-            "count": 10
+            "value": 2.383786090983552e-07,
+            "min": 2.383786090983552e-07,
+            "max": 4.3855083742622895e-06,
+            "count": 9
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 6.052247982750011e-06,
-            "min": 6.052247982750011e-06,
-            "max": 0.00010651946449366663,
-            "count": 10
+            "value": 2.383786090983552e-07,
+            "min": 2.383786090983552e-07,
+            "max": 4.3855083742622895e-06,
+            "count": 9
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10040345000000002,
-            "min": 0.10040345000000002,
-            "max": 0.10789566666666667,
-            "count": 10
+            "value": 0.10003971311475411,
+            "min": 0.10003971311475411,
+            "max": 0.10073090163934427,
+            "count": 9
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 0.5020172500000001,
-            "min": 0.40827458333333333,
-            "max": 0.5355063333333333,
-            "count": 10
+            "value": 0.10003971311475411,
+            "min": 0.10003971311475411,
+            "max": 0.10073090163934427,
+            "count": 9
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 5.030465500000008e-05,
-            "min": 5.030465500000008e-05,
-            "max": 0.0007987771000000001,
-            "count": 10
+            "value": 1.793468032786867e-05,
+            "min": 1.793468032786867e-05,
+            "max": 0.00015603414754098344,
+            "count": 9
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0002515232750000004,
-            "min": 0.0002515232750000004,
-            "max": 0.0035970826999999995,
-            "count": 10
+            "value": 1.793468032786867e-05,
+            "min": 1.793468032786867e-05,
+            "max": 0.00015603414754098344,
+            "count": 9
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.007879960350692272,
-            "min": 0.007417359855026007,
-            "max": 0.008922145701944828,
-            "count": 10
+            "value": 0.007509872782975435,
+            "min": 0.006891245488077402,
+            "max": 0.008904346264898777,
+            "count": 9
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.039399802684783936,
-            "min": 0.03265004605054855,
-            "max": 0.04405519366264343,
-            "count": 10
-        },
-        "Pyramids.IsTraining.mean": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 10
-        },
-        "Pyramids.IsTraining.sum": {
-            "value": 1.0,
-            "min": 1.0,
-            "max": 1.0,
-            "count": 10
+            "value": 0.007509872782975435,
+            "min": 0.006891245488077402,
+            "max": 0.008904346264898777,
+            "count": 9
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1694051628",
+        "start_time_seconds": "1694051995",
         "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": "1694051936"
+        "end_time_seconds": "1694052059"
     },
-    "total": 307.83498315999987,
+    "total": 63.78960916400047,
     "count": 1,
-    "self": 0.9932788870000877,
+    "self": 0.5258810410005026,
     "children": {
         "run_training.setup": {
-            "total": 0.04420855799980927,
+            "total": 0.05054371200003516,
             "count": 1,
-            "self": 0.04420855799980927
+            "self": 0.05054371200003516
         },
         "TrainerController.start_learning": {
-            "total": 306.79749571499997,
+            "total": 63.21318441099993,
             "count": 1,
-            "self": 0.20744312998976966,
+            "self": 0.04291654601729533,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.416401536999729,
+                    "total": 4.393879314000515,
                     "count": 1,
-                    "self": 4.416401536999729
+                    "self": 4.393879314000515
                 },
                 "TrainerController.advance": {
-                    "total": 301.9820236040114,
-                    "count": 6562,
-                    "self": 0.20287413097139506,
+                    "total": 58.64456017098291,
+                    "count": 1356,
+                    "self": 0.040323003963749215,
                     "children": {
                         "env_step": {
-                            "total": 226.59980304005967,
-                            "count": 6562,
-                            "self": 212.69486092499756,
+                            "total": 44.12480102901645,
+                            "count": 1356,
+                            "self": 41.25797055703151,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 13.785187271016184,
-                                    "count": 6562,
-                                    "self": 0.5929621260129352,
+                                    "total": 2.8443501229912727,
+                                    "count": 1356,
+                                    "self": 0.129180536986496,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 13.192225145003249,
-                                            "count": 6305,
-                                            "self": 13.192225145003249
+                                            "total": 2.7151695860047766,
+                                            "count": 1312,
+                                            "self": 2.7151695860047766
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.11975484404592862,
-                                    "count": 6562,
+                                    "total": 0.022480348993667576,
+                                    "count": 1356,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 305.9035596379754,
-                                            "count": 6562,
+                                            "total": 62.98079351200431,
+                                            "count": 1356,
                                             "is_parallel": true,
-                                            "self": 108.05694014095388,
+                                            "self": 24.771973838007398,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0018208730007245322,
+                                                            "total": 0.0017561280001245905,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005818830013595289,
+                                                            "self": 0.0005503700022018165,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012389899993650033,
+                                                                    "total": 0.001205757997922774,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012389899993650033
+                                                                    "self": 0.001205757997922774
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06126133799989475,
+                                                            "total": 0.05420530500032328,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006589589993382106,
+                                                            "self": 0.0006800420005674823,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005435650000435999,
+                                                                    "total": 0.0004770069999722182,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005435650000435999
+                                                                    "self": 0.0004770069999722182
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05777589399986027,
+                                                                    "total": 0.050895364999632875,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05777589399986027
+                                                                    "self": 0.050895364999632875
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002282920000652666,
+                                                                    "total": 0.002152891000150703,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045695199969486566,
+                                                                    "self": 0.0004335960011303541,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0018259680009578005,
+                                                                            "total": 0.0017192949990203488,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0018259680009578005
+                                                                            "self": 0.0017192949990203488
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 197.8466194970215,
-                                                    "count": 6561,
+                                                    "total": 38.20881967399691,
+                                                    "count": 1355,
                                                     "is_parallel": true,
-                                                    "self": 4.055203757041454,
+                                                    "self": 0.8366514489862311,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.657970951977404,
-                                                            "count": 6561,
+                                                            "total": 0.5423410720050015,
+                                                            "count": 1355,
                                                             "is_parallel": true,
-                                                            "self": 2.657970951977404
+                                                            "self": 0.5423410720050015
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 178.68335932797527,
-                                                            "count": 6561,
+                                                            "total": 34.27706771701378,
+                                                            "count": 1355,
                                                             "is_parallel": true,
-                                                            "self": 178.68335932797527
+                                                            "self": 34.27706771701378
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 12.450085460027367,
-                                                            "count": 6561,
+                                                            "total": 2.552759435991902,
+                                                            "count": 1355,
                                                             "is_parallel": true,
-                                                            "self": 2.5430296750582784,
+                                                            "self": 0.5401004210198153,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 9.907055784969089,
-                                                                    "count": 52488,
+                                                                    "total": 2.012659014972087,
+                                                                    "count": 10840,
                                                                     "is_parallel": true,
-                                                                    "self": 9.907055784969089
+                                                                    "self": 2.012659014972087
                                                                 }
                                                             }
                                                         }
@@ -343,24 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 75.17934643298031,
-                            "count": 6562,
-                            "self": 0.3588888639887955,
+                            "total": 14.479436138002711,
+                            "count": 1356,
+                            "self": 0.07078761600314465,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 12.963260964991605,
-                                    "count": 6562,
-                                    "self": 12.963260964991605
+                                    "total": 2.707153262999782,
+                                    "count": 1356,
+                                    "self": 2.707153262999782
                                 },
                                 "_update_policy": {
-                                    "total": 61.85719660399991,
-                                    "count": 47,
-                                    "self": 40.133688856989465,
+                                    "total": 11.701495258999785,
+                                    "count": 9,
+                                    "self": 7.711733383001956,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 21.723507747010444,
-                                            "count": 2265,
-                                            "self": 21.723507747010444
+                                            "total": 3.9897618759978286,
+                                            "count": 432,
+                                            "self": 3.9897618759978286
                                         }
                                     }
                                 }
@@ -369,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.6289995983242989e-06,
+                    "total": 9.429995770915411e-07,
                     "count": 1,
-                    "self": 1.6289995983242989e-06
+                    "self": 9.429995770915411e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.19162581499949738,
+                    "total": 0.13182743699962884,
                     "count": 1,
-                    "self": 0.002327421999325452,
+                    "self": 0.0019178709999323473,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18929839300017193,
+                            "total": 0.1299095659996965,
                             "count": 1,
-                            "self": 0.18929839300017193
+                            "self": 0.1299095659996965
                         }
                     }
                 }

run_logs/training_status.json

@@ -6,24 +6,6 @@
     },
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499885,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499885.onnx",
-                "reward": null,
-                "creation_time": 1694048654.0054872,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499885.pt"
-                ]
-            },
-            {
-                "steps": 999955,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999955.onnx",
-                "reward": 1.664499968290329,
-                "creation_time": 1694050034.4300313,
-                "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999955.pt"
-                ]
-            },
             {
                 "steps": 1000083,
                 "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000083.onnx",
@@ -50,15 +32,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-1200040.pt"
                 ]
+            },
+            {
+                "steps": 1200040,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1200040.onnx",
+                "reward": null,
+                "creation_time": 1694051970.359339,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1200040.pt"
+                ]
+            },
+            {
+                "steps": 1220046,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1220046.onnx",
+                "reward": 1.6854999959468842,
+                "creation_time": 1694052058.6380424,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1220046.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1200040,
+            "steps": 1220046,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1694051935.8271642,
+            "reward": 1.6854999959468842,
+            "creation_time": 1694052058.6380424,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1200040.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1220046.pt"
             ]
         }
     }