First Pyramids

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02d7d3d09edd3a3f2cae07a53de9a4b9e9671c3dda7a7739ba7caff0c562992
+oid sha256:33aed2cf5bdf0fa3e5242c245428b9028be3578d3642c32844cb26032861a5cb
 size 1417437

Pyramids/Pyramids-499920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1de2c3b990b24eebbdab42c6b9ff8c7a254ba26fe96eaea9f8e2b1831c24bf2
+size 1417437

Pyramids/Pyramids-499920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa385df94098e6cee0bff2e36f3e6135ff80a0f33fd80f25ba624d50e25d57e5
+size 8652382

Pyramids/Pyramids-900074.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33aed2cf5bdf0fa3e5242c245428b9028be3578d3642c32844cb26032861a5cb
+size 1417437

Pyramids/Pyramids-900074.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:566cdf948738930d55b4d93224cff1e4f02e40ac4b51246e7090786c75c723e3
+size 8652382

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5613408368331603d747fe87eb6552cf665f3418dca7fac30f7e99199b9089
+oid sha256:566cdf948738930d55b4d93224cff1e4f02e40ac4b51246e7090786c75c723e3
 size 8652382

Pyramids/{events.out.tfevents.1663034178.89814b316157.250.0 → events.out.tfevents.1663037989.89814b316157.715.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9db2412be8cc7654913e18dae4c5789c3bbc8f109d9cd17a97de2688dd61cbc
-size 147747
+oid sha256:d20b694c45e835a29ca3f319fd147b13f19cfd2900d33782638d578335336126
+size 292932

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 500000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 900000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -49,7 +49,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     checkpoint_interval: 500000
-    max_steps: 500000
+    max_steps: 900000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -79,7 +79,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 1 interfaces on host : 0) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55001 [Flags] 2 [Guid] 2569274264 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55477 [Flags] 2 [Guid] 1490386777 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2495:(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  0.086 seconds
+- Completed reload, in  0.087 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)
@@ -68,7 +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: 0.897008 ms
+UnloadTime: 0.840575 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.
@@ -76,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 4401 frames, [32.0 KB-64.0 KB]: 4286 frames, [64.0 KB-128.0 KB]: 707 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 3148 frames, [32.0 KB-64.0 KB]: 10347 frames, [64.0 KB-128.0 KB]: 3398 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
@@ -207,25 +204,25 @@ 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]: 9096 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 16595 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 12887
+  Peak main deferred allocation count 12856
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 9394 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 16893 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.8 MB
+      Peak Allocated memory 29.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 9395 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 16894 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 24.2 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 9394 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 16893 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]: 9395 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 16894 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,13 +272,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 9096 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 16595 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]: 9394 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 16893 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
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 9395 frames
+      Peak usage frame count: [0-1.0 KB]: 16894 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]: 9395 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 16894 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]: 9395 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 16894 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":1663035121899,"processId":263,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3444},{"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":1663039910663,"processId":726,"allocatedMemory":1957329,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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":3444},{"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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.8551792502403259,
-            "min": 0.7987250685691833,
-            "max": 1.4379101991653442,
-            "count": 16
+            "value": 0.3143894672393799,
+            "min": 0.3018721044063568,
+            "max": 1.5173466205596924,
+            "count": 30
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 25545.9140625,
-            "min": 23808.396484375,
-            "max": 43620.4453125,
-            "count": 16
+            "value": 9461.865234375,
+            "min": 9089.97265625,
+            "max": 46030.2265625,
+            "count": 30
         },
         "Pyramids.Step.mean": {
-            "value": 479899.0,
+            "value": 899946.0,
             "min": 29952.0,
-            "max": 479899.0,
-            "count": 16
+            "max": 899946.0,
+            "count": 30
         },
         "Pyramids.Step.sum": {
-            "value": 479899.0,
+            "value": 899946.0,
             "min": 29952.0,
-            "max": 479899.0,
-            "count": 16
+            "max": 899946.0,
+            "count": 30
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.041768331080675125,
-            "min": -0.23297199606895447,
-            "max": 0.041768331080675125,
-            "count": 16
+            "value": 0.5661607980728149,
+            "min": -0.07692617923021317,
+            "max": 0.6612709760665894,
+            "count": 30
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 10.275009155273438,
-            "min": -55.21436309814453,
-            "max": 10.275009155273438,
-            "count": 16
+            "value": 156.8265380859375,
+            "min": -18.69306182861328,
+            "max": 189.38992309570312,
+            "count": 30
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.02816394902765751,
-            "min": 0.016801640391349792,
-            "max": 0.462855726480484,
-            "count": 16
+            "value": 0.0005080682458356023,
+            "min": -0.020590951666235924,
+            "max": 0.17304767668247223,
+            "count": 30
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 6.92833137512207,
-            "min": 4.082798480987549,
-            "max": 109.69680786132812,
-            "count": 16
+            "value": 0.14073491096496582,
+            "min": -5.847830295562744,
+            "max": 41.704490661621094,
+            "count": 30
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06891248585682862,
-            "min": 0.0674254671509026,
-            "max": 0.07210142848894119,
-            "count": 16
+            "value": 0.0680910766488564,
+            "min": 0.06459918983108807,
+            "max": 0.07283377598440792,
+            "count": 30
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9647748019956006,
-            "min": 0.5047099994225883,
-            "max": 0.994451392206214,
-            "count": 16
+            "value": 0.9532750730839896,
+            "min": 0.49954552701527205,
+            "max": 1.0925066397661187,
+            "count": 30
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.005975904033627357,
-            "min": 0.00024290360250985284,
-            "max": 0.010059403508146592,
-            "count": 16
+            "value": 0.014839827194575128,
+            "min": 0.0007602584838577493,
+            "max": 0.017616673432187074,
+            "count": 30
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.083662656470783,
-            "min": 0.0029148432301182342,
-            "max": 0.08456777552173128,
-            "count": 16
+            "value": 0.2077575807240518,
+            "min": 0.006842326354719744,
+            "max": 0.2642501014828061,
+            "count": 30
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.1505635688628576e-05,
-            "min": 2.1505635688628576e-05,
-            "max": 0.00029030126037577137,
-            "count": 16
+            "value": 5.024241182428572e-06,
+            "min": 5.024241182428572e-06,
+            "max": 0.000294611811319873,
+            "count": 30
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00030107889964080004,
-            "min": 0.00030107889964080004,
-            "max": 0.0028543166485612,
-            "count": 16
+            "value": 7.033937655400001e-05,
+            "min": 7.033937655400001e-05,
+            "max": 0.003448268817243777,
+            "count": 30
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10716851428571429,
-            "min": 0.10716851428571429,
-            "max": 0.19676708571428575,
-            "count": 16
+            "value": 0.10167471428571428,
+            "min": 0.10167471428571428,
+            "max": 0.1982039365079365,
+            "count": 30
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5003592000000001,
-            "min": 1.3773696000000002,
-            "max": 2.251103,
-            "count": 16
+            "value": 1.423446,
+            "min": 1.3874275555555555,
+            "max": 2.544346777777778,
+            "count": 30
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0007261345771428573,
-            "min": 0.0007261345771428573,
-            "max": 0.00967703186285714,
-            "count": 16
+            "value": 0.00017730395714285715,
+            "min": 0.00017730395714285715,
+            "max": 0.00982057325714286,
+            "count": 30
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.010165884080000001,
-            "min": 0.010165884080000001,
-            "max": 0.09516873611999999,
-            "count": 16
+            "value": 0.0024822554,
+            "min": 0.0024822554,
+            "max": 0.11495734660000001,
+            "count": 30
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.024871766567230225,
-            "min": 0.024871766567230225,
-            "max": 0.5086265802383423,
-            "count": 16
+            "value": 0.010926744900643826,
+            "min": 0.010926744900643826,
+            "max": 0.36154836416244507,
+            "count": 30
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.34820473194122314,
-            "min": 0.34820473194122314,
-            "max": 3.5603859424591064,
-            "count": 16
+            "value": 0.1529744267463684,
+            "min": 0.1529744267463684,
+            "max": 2.5308384895324707,
+            "count": 30
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 856.3513513513514,
-            "min": 826.8055555555555,
+            "value": 357.8,
+            "min": 279.5904761904762,
             "max": 999.0,
-            "count": 16
+            "count": 30
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 31685.0,
+            "value": 30413.0,
             "min": 15984.0,
-            "max": 32410.0,
-            "count": 16
+            "max": 32523.0,
+            "count": 30
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": -0.04591355533213229,
+            "value": 1.6186611538424212,
             "min": -1.0000000521540642,
-            "max": -0.04591355533213229,
-            "count": 16
+            "max": 1.7013561763933727,
+            "count": 30
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": -1.6988015472888947,
-            "min": -31.9980016797781,
-            "max": -1.6988015472888947,
-            "count": 16
+            "value": 137.5861980766058,
+            "min": -30.55440167337656,
+            "max": 178.64239852130413,
+            "count": 30
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": -0.04591355533213229,
+            "value": 1.6186611538424212,
             "min": -1.0000000521540642,
-            "max": -0.04591355533213229,
-            "count": 16
+            "max": 1.7013561763933727,
+            "count": 30
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": -1.6988015472888947,
-            "min": -31.9980016797781,
-            "max": -1.6988015472888947,
-            "count": 16
+            "value": 137.5861980766058,
+            "min": -30.55440167337656,
+            "max": 178.64239852130413,
+            "count": 30
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.21981896639752793,
-            "min": 0.21981896639752793,
-            "max": 10.510865385644138,
-            "count": 16
+            "value": 0.0404436282477999,
+            "min": 0.033162879603748606,
+            "max": 7.883609194308519,
+            "count": 30
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 8.133301756708534,
-            "min": 8.133301756708534,
-            "max": 168.1738461703062,
-            "count": 16
+            "value": 3.4377084010629915,
+            "min": 3.4377084010629915,
+            "max": 126.13774710893631,
+            "count": 30
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 30
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 16
+            "count": 30
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1663034172",
+        "start_time_seconds": "1663037986",
         "python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1663035121"
+        "end_time_seconds": "1663039910"
     },
-    "total": 949.486580744,
+    "total": 1924.2608588920002,
     "count": 1,
-    "self": 0.5306857950001813,
+    "self": 0.4412678379994759,
     "children": {
         "run_training.setup": {
-            "total": 0.04314515199996549,
+            "total": 0.04964085200026602,
             "count": 1,
-            "self": 0.04314515199996549
+            "self": 0.04964085200026602
         },
         "TrainerController.start_learning": {
-            "total": 948.9127497969998,
+            "total": 1923.7699502020005,
             "count": 1,
-            "self": 0.6094973130024073,
+            "self": 1.2086384270623967,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.497055248000038,
+                    "total": 5.598036690000299,
                     "count": 1,
-                    "self": 8.497055248000038
+                    "self": 5.598036690000299
                 },
                 "TrainerController.advance": {
-                    "total": 939.7103127629973,
-                    "count": 31563,
-                    "self": 0.6678566289798482,
+                    "total": 1916.8633218839377,
+                    "count": 57825,
+                    "self": 1.2712493989183713,
                     "children": {
                         "env_step": {
-                            "total": 601.6391101400013,
-                            "count": 31563,
-                            "self": 552.0577899270065,
+                            "total": 1298.6090012799514,
+                            "count": 57825,
+                            "self": 1209.6398991310298,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 49.25383562500173,
-                                    "count": 31563,
-                                    "self": 2.252808151003933,
+                                    "total": 88.3406368768292,
+                                    "count": 57825,
+                                    "self": 4.105943385953651,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 47.001027473997794,
-                                            "count": 31315,
-                                            "self": 16.831620127982603,
+                                            "total": 84.23469349087554,
+                                            "count": 56312,
+                                            "self": 30.080371604844004,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 30.16940734601519,
-                                                    "count": 31315,
-                                                    "self": 30.16940734601519
+                                                    "total": 54.15432188603154,
+                                                    "count": 56312,
+                                                    "self": 54.15432188603154
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.3274845879930126,
-                                    "count": 31563,
+                                    "total": 0.6284652720923987,
+                                    "count": 57825,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 946.8978322339931,
-                                            "count": 31563,
+                                            "total": 1920.4270927631842,
+                                            "count": 57825,
                                             "is_parallel": true,
-                                            "self": 442.83670484899596,
+                                            "self": 799.8686832981284,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005172546000039802,
+                                                            "total": 0.0019791639997492894,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0039040570001134256,
+                                                            "self": 0.0007899419988461887,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001268488999926376,
+                                                                    "total": 0.0011892220009031007,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001268488999926376
+                                                                    "self": 0.0011892220009031007
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.058935512999994444,
+                                                            "total": 0.04400810700008151,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005064509999783695,
+                                                            "self": 0.0005137100006322726,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004569000000174128,
+                                                                    "total": 0.0004628869992302498,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004569000000174128
+                                                                    "self": 0.0004628869992302498
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.056343545999993694,
+                                                                    "total": 0.04134547699959512,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.056343545999993694
+                                                                    "self": 0.04134547699959512
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016286160000049676,
+                                                                    "total": 0.0016860330006238655,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004844880000973717,
+                                                                    "self": 0.0003958099996452802,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001144127999907596,
+                                                                            "total": 0.0012902230009785853,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001144127999907596
+                                                                            "self": 0.0012902230009785853
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 504.0611273849971,
-                                                    "count": 31562,
+                                                    "total": 1120.5584094650558,
+                                                    "count": 57824,
                                                     "is_parallel": true,
-                                                    "self": 13.731320075961946,
+                                                    "self": 24.905355304088516,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 11.008401622007227,
-                                                            "count": 31562,
+                                                            "total": 20.177002000952598,
+                                                            "count": 57824,
                                                             "is_parallel": true,
-                                                            "self": 11.008401622007227
+                                                            "self": 20.177002000952598
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 434.18997510500793,
-                                                            "count": 31562,
+                                                            "total": 993.9248567621398,
+                                                            "count": 57824,
                                                             "is_parallel": true,
-                                                            "self": 434.18997510500793
+                                                            "self": 993.9248567621398
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 45.131430582020016,
-                                                            "count": 31562,
+                                                            "total": 81.55119539787484,
+                                                            "count": 57824,
                                                             "is_parallel": true,
-                                                            "self": 11.140580420044785,
+                                                            "self": 20.30215880967353,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 33.99085016197523,
-                                                                    "count": 252496,
+                                                                    "total": 61.24903658820131,
+                                                                    "count": 462592,
                                                                     "is_parallel": true,
-                                                                    "self": 33.99085016197523
+                                                                    "self": 61.24903658820131
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 337.40334599401615,
-                            "count": 31563,
-                            "self": 1.0201980530133596,
+                            "total": 616.983071205068,
+                            "count": 57825,
+                            "self": 2.2400394880751264,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 76.00806477000111,
-                                    "count": 31563,
-                                    "self": 75.78988363200102,
+                                    "total": 139.49717225100903,
+                                    "count": 57825,
+                                    "self": 139.38434084000892,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.21818113800009087,
+                                            "total": 0.11283141100011562,
                                             "count": 1,
-                                            "self": 0.21818113800009087
+                                            "self": 0.11283141100011562
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 260.3750831710017,
-                                    "count": 210,
-                                    "self": 104.87488389200303,
+                                    "total": 475.2458594659838,
+                                    "count": 405,
+                                    "self": 190.12632660298823,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 155.50019927899865,
-                                            "count": 11421,
-                                            "self": 155.50019927899865
+                                            "total": 285.1195328629956,
+                                            "count": 20529,
+                                            "self": 285.1195328629956
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.1180000001331791e-06,
+                    "total": 1.1410002116463147e-06,
                     "count": 1,
-                    "self": 1.1180000001331791e-06
+                    "self": 1.1410002116463147e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09588335500006906,
+                    "total": 0.09995205999985046,
                     "count": 1,
-                    "self": 0.0017003719999593159,
+                    "self": 0.0020695530001830775,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09418298300010974,
+                            "total": 0.09788250699966738,
                             "count": 1,
-                            "self": 0.09418298300010974
+                            "self": 0.09788250699966738
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,31 +2,31 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499924,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499924.onnx",
-                "reward": null,
-                "creation_time": 1663035121.2961612,
+                "steps": 499920,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499920.onnx",
+                "reward": 1.9520000219345093,
+                "creation_time": 1663039006.5182111,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499924.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-499920.pt"
                 ]
             },
             {
-                "steps": 500052,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-500052.onnx",
-                "reward": null,
-                "creation_time": 1663035121.40716,
+                "steps": 900074,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-900074.onnx",
+                "reward": 1.6816666424274445,
+                "creation_time": 1663039910.2576778,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-500052.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-900074.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 500052,
+            "steps": 900074,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1663035121.40716,
+            "reward": 1.6816666424274445,
+            "creation_time": 1663039910.2576778,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-500052.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-900074.pt"
             ]
         }
     },