Update with longer training

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527ebaccc5eb3da41f020892161eab6b32f12801016e39b49b219d7201d9ca14
+oid sha256:8a5bb38073219186f6ea31e6c227e1c08270a761cba878e31cdd984acb7cc5a8
 size 1417437

Pyramids/Pyramids-1499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1304f52b41d6b65334b6a30fd7e1a946e017d0ee9779fcd30f77fd0b78da4337
+size 1417437

Pyramids/Pyramids-1499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9132764831bb400ac9fdbc07866a2f08fbde36134e501af589d9c1d896507769
+size 8652382

Pyramids/Pyramids-1999965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6dd61c1da154526adf8ac590d052848f43ac83a9704549bf3c0c0ef25e03dfa
+size 1417437

Pyramids/Pyramids-1999965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f4a0c541921c1ec7fca79b9a6b8cedb91489f27304fba49254e38bfbd3e40f1
+size 8652382

Pyramids/Pyramids-2499926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380e73ee0f93f1dd71cd042e054e28530d9f854b19c4603e65301a18dbffd298
+size 1417437

Pyramids/Pyramids-2499926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da46ca55012eaee246ad555196d496301e14700fc5486653e292a13e1bf5a8cc
+size 8652382

Pyramids/Pyramids-2999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5bb38073219186f6ea31e6c227e1c08270a761cba878e31cdd984acb7cc5a8
+size 1417437

Pyramids/Pyramids-2999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927e712efb8a00f24a6caad52384a33610bd6f130831d3ad439c322a40ae3ea8
+size 8652446

Pyramids/Pyramids-3000054.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a5bb38073219186f6ea31e6c227e1c08270a761cba878e31cdd984acb7cc5a8
+size 1417437

Pyramids/Pyramids-3000054.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fe78fe258b0f6baac658b234b941a8d08796db9b5f9eebacafe4a6ff11877e
+size 8652446

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f852c4eeca8d297db7ff3bd37c76c74912e1231e5a8df440e788faea0b603595
-size 8652382
+oid sha256:02fe78fe258b0f6baac658b234b941a8d08796db9b5f9eebacafe4a6ff11877e
+size 8652446

Pyramids/{events.out.tfevents.1673865214.60c9236efe87.1383.0 → events.out.tfevents.1673867810.60c9236efe87.12550.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad1d6e2bb864e31cbeeabad1b7c63bef3c393b956eecfe78197e453e286256f6
-size 332514
+oid sha256:7a992d71f8003af989cdd2f3d202b8470a86f9eb008fc1cc5f47893873f51fd9
+size 896138

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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": 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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": 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: 1000000
+    max_steps: 3000000
     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/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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55434 [Flags] 2 [Guid] 146653094 [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] 55253 [Flags] 2 [Guid] 2038515196 [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/training-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  0.078 seconds
+- Completed reload, in  0.082 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: 0.778983 ms
+UnloadTime: 0.740791 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]: 7879 frames, [32.0 KB-64.0 KB]: 9331 frames, [64.0 KB-128.0 KB]: 1560 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7730 frames, [32.0 KB-64.0 KB]: 32769 frames, [64.0 KB-128.0 KB]: 15765 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
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +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
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 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 10915
+  Peak main deferred allocation count 12856
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 152 frames, [16.0 MB-32.0 MB]: 18619 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 56264 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 28.8 MB
+      Peak Allocated memory 31.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.6 MB
+      Peak Allocated memory 21.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56264 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]: 18771 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 56265 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      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]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55966 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]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 56264 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
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.6 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 56265 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]: 18771 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56265 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]: 18771 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 56265 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +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":1673867202688,"processId":1404,"allocatedMemory":1957332,"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":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":1673874672000,"processId":12567,"allocatedMemory":1957332,"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":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

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.7462787628173828,
-            "min": 0.6699330806732178,
-            "max": 1.4639549255371094,
-            "count": 33
+            "value": 0.1675790548324585,
+            "min": 0.16217057406902313,
+            "max": 1.3953831195831299,
+            "count": 100
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 22471.9453125,
-            "min": 20087.2734375,
-            "max": 44410.53515625,
-            "count": 33
+            "value": 5030.052734375,
+            "min": 4826.1962890625,
+            "max": 42330.34375,
+            "count": 100
         },
         "Pyramids.Step.mean": {
-            "value": 989949.0,
+            "value": 2999926.0,
             "min": 29952.0,
-            "max": 989949.0,
-            "count": 33
+            "max": 2999926.0,
+            "count": 100
         },
         "Pyramids.Step.sum": {
-            "value": 989949.0,
+            "value": 2999926.0,
             "min": 29952.0,
-            "max": 989949.0,
-            "count": 33
+            "max": 2999926.0,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.18282149732112885,
-            "min": -0.09427541494369507,
-            "max": 0.18282149732112885,
-            "count": 33
+            "value": 0.8224744200706482,
+            "min": -0.2121364027261734,
+            "max": 0.9010592103004456,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 46.25383758544922,
-            "min": -22.720375061035156,
-            "max": 46.25383758544922,
-            "count": 33
+            "value": 245.09738159179688,
+            "min": -50.276329040527344,
+            "max": 283.0172119140625,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.04315521568059921,
-            "min": -0.04315521568059921,
-            "max": 0.47724154591560364,
-            "count": 33
+            "value": -0.000254911050433293,
+            "min": -0.02823013626039028,
+            "max": 0.7119223475456238,
+            "count": 100
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -10.918269157409668,
-            "min": -10.918269157409668,
-            "max": 113.10624694824219,
-            "count": 33
+            "value": -0.07596348971128464,
+            "min": -8.327890396118164,
+            "max": 168.72560119628906,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06743275307969018,
-            "min": 0.06486022301381414,
-            "max": 0.07289904453973475,
-            "count": 33
+            "value": 0.0689286315149327,
+            "min": 0.06372497180786248,
+            "max": 0.07353446988962167,
+            "count": 100
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9440585431156625,
-            "min": 0.5016881638098154,
-            "max": 1.03840414700144,
-            "count": 33
+            "value": 0.9650008412090578,
+            "min": 0.4994683060644532,
+            "max": 1.086479228603375,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.009502245228721206,
-            "min": 0.0007019426463068361,
-            "max": 0.009502245228721206,
-            "count": 33
+            "value": 0.013487047703068635,
+            "min": 0.00011577515347134225,
+            "max": 0.03296545092176792,
+            "count": 100
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1330314332020969,
-            "min": 0.009827197048295705,
-            "max": 0.1330314332020969,
-            "count": 33
+            "value": 0.1888186678429609,
+            "min": 0.0015050769951274494,
+            "max": 0.23508479958343065,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.238411872942855e-06,
-            "min": 7.238411872942855e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.5662709065142888e-06,
+            "min": 1.5662709065142888e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010133776622119997,
-            "min": 0.00010133776622119997,
-            "max": 0.0033759616746795004,
-            "count": 33
+            "value": 2.1927792691200042e-05,
+            "min": 2.1927792691200042e-05,
+            "max": 0.0039273318908894,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10241277142857143,
-            "min": 0.10241277142857143,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10052205714285714,
+            "min": 0.10052205714285714,
+            "max": 0.19946118095238097,
+            "count": 100
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4337788,
-            "min": 1.3886848,
-            "max": 2.4253205000000007,
-            "count": 33
+            "value": 1.4073088,
+            "min": 1.3962282666666668,
+            "max": 2.7675394666666664,
+            "count": 100
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025103586571428567,
-            "min": 0.00025103586571428567,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 6.215350857142868e-05,
+            "min": 6.215350857142868e-05,
+            "max": 0.009946171977142856,
+            "count": 100
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003514502119999999,
-            "min": 0.003514502119999999,
-            "max": 0.11254951794999998,
-            "count": 33
+            "value": 0.0008701491200000015,
+            "min": 0.0008701491200000015,
+            "max": 0.13092014894,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.011206984519958496,
-            "min": 0.011206984519958496,
-            "max": 0.48932430148124695,
-            "count": 33
+            "value": 0.005784022156149149,
+            "min": 0.005301194731146097,
+            "max": 0.9048455357551575,
+            "count": 100
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.15689778327941895,
-            "min": 0.15689778327941895,
-            "max": 3.4252700805664062,
-            "count": 33
+            "value": 0.08097630739212036,
+            "min": 0.0795179232954979,
+            "max": 6.333918571472168,
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 690.9767441860465,
-            "min": 690.9767441860465,
+            "value": 219.42335766423358,
+            "min": 188.53048780487805,
             "max": 999.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29712.0,
+            "value": 30061.0,
             "min": 15984.0,
-            "max": 33881.0,
-            "count": 33
+            "max": 32828.0,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.8566545151512731,
+            "value": 1.7805766305566704,
             "min": -1.0000000521540642,
-            "max": 0.8566545151512731,
-            "count": 33
+            "max": 1.7994674732165834,
+            "count": 100
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 37.69279866665602,
-            "min": -30.043001666665077,
-            "max": 37.69279866665602,
-            "count": 33
+            "value": 243.93899838626385,
+            "min": -31.998001664876938,
+            "max": 293.3131981343031,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.8566545151512731,
+            "value": 1.7805766305566704,
             "min": -1.0000000521540642,
-            "max": 0.8566545151512731,
-            "count": 33
+            "max": 1.7994674732165834,
+            "count": 100
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 37.69279866665602,
-            "min": -30.043001666665077,
-            "max": 37.69279866665602,
-            "count": 33
+            "value": 243.93899838626385,
+            "min": -31.998001664876938,
+            "max": 293.3131981343031,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.08061111984187103,
-            "min": 0.08061111984187103,
-            "max": 9.825890893116593,
-            "count": 33
+            "value": 0.013117933525870823,
+            "min": 0.011766130464050888,
+            "max": 19.960637274198234,
+            "count": 100
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 3.546889273042325,
-            "min": 3.475608774169814,
-            "max": 157.2142542898655,
-            "count": 33
+            "value": 1.7971568930443027,
+            "min": 1.6039180451552966,
+            "max": 319.37019638717175,
+            "count": 100
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 100
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673865207",
+        "start_time_seconds": "1673867807",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "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",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --force --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
         "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": "1673867202"
+        "end_time_seconds": "1673874672"
     },
-    "total": 1995.039878496,
+    "total": 6864.8881963250005,
     "count": 1,
-    "self": 0.4469459450001523,
+    "self": 0.42651065999962157,
     "children": {
         "run_training.setup": {
-            "total": 0.12174109699998326,
+            "total": 0.10514022699999259,
             "count": 1,
-            "self": 0.12174109699998326
+            "self": 0.10514022699999259
         },
         "TrainerController.start_learning": {
-            "total": 1994.4711914539998,
+            "total": 6864.3565454380005,
             "count": 1,
-            "self": 1.1549643369914975,
+            "self": 3.772354387128871,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.073733354000012,
+                    "total": 6.280578569000227,
                     "count": 1,
-                    "self": 10.073733354000012
+                    "self": 6.280578569000227
                 },
                 "TrainerController.advance": {
-                    "total": 1983.1499018210086,
-                    "count": 63168,
-                    "self": 1.228186820990004,
+                    "total": 6854.216574231871,
+                    "count": 195003,
+                    "self": 4.004867659939009,
                     "children": {
                         "env_step": {
-                            "total": 1313.3889008609858,
-                            "count": 63168,
-                            "self": 1212.466975328011,
+                            "total": 4870.815900672944,
+                            "count": 195003,
+                            "self": 4559.99746307044,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 100.18658557998856,
-                                    "count": 63168,
-                                    "self": 4.129120996911297,
+                                    "total": 308.43615814668783,
+                                    "count": 195003,
+                                    "self": 12.661934140508492,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 96.05746458307726,
-                                            "count": 62569,
-                                            "self": 32.707439445102295,
+                                            "total": 295.77422400617934,
+                                            "count": 187550,
+                                            "self": 99.84544257111293,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 63.35002513797497,
-                                                    "count": 62569,
-                                                    "self": 63.35002513797497
+                                                    "total": 195.9287814350664,
+                                                    "count": 187550,
+                                                    "self": 195.9287814350664
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7353399529864078,
-                                    "count": 63168,
+                                    "total": 2.382279455815933,
+                                    "count": 195003,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1990.653330305974,
-                                            "count": 63168,
+                                            "total": 6850.26255202094,
+                                            "count": 195003,
                                             "is_parallel": true,
-                                            "self": 873.2833848129385,
+                                            "self": 2589.9094462507464,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005672554999989643,
+                                                            "total": 0.0016592880001553567,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0033566940001037437,
+                                                            "self": 0.0006072650007808988,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0023158609998858992,
+                                                                    "total": 0.0010520229993744579,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0023158609998858992
+                                                                    "self": 0.0010520229993744579
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.044894693999992796,
+                                                            "total": 0.06567906500004028,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000494175999961044,
+                                                            "self": 0.0005069389994787343,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00045645599999488695,
+                                                                    "total": 0.0003919000000678352,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00045645599999488695
+                                                                    "self": 0.0003919000000678352
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0422164359999897,
+                                                                    "total": 0.06307000100014193,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0422164359999897
+                                                                    "self": 0.06307000100014193
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017276260000471666,
+                                                                    "total": 0.0017102250003517838,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004448190000516661,
+                                                                    "self": 0.0004076020004504244,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0012828069999955005,
+                                                                            "total": 0.0013026229999013594,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0012828069999955005
+                                                                            "self": 0.0013026229999013594
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1117.3699454930354,
-                                                    "count": 63167,
+                                                    "total": 4260.353105770194,
+                                                    "count": 195002,
                                                     "is_parallel": true,
-                                                    "self": 27.908301036023886,
+                                                    "self": 84.96059891143796,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.443457706992547,
-                                                            "count": 63167,
+                                                            "total": 66.24082947365332,
+                                                            "count": 195002,
                                                             "is_parallel": true,
-                                                            "self": 22.443457706992547
+                                                            "self": 66.24082947365332
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 975.5978612890058,
-                                                            "count": 63167,
+                                                            "total": 3806.085641901141,
+                                                            "count": 195002,
                                                             "is_parallel": true,
-                                                            "self": 975.5978612890058
+                                                            "self": 3806.085641901141
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 91.42032546101308,
-                                                            "count": 63167,
+                                                            "total": 303.06603548396106,
+                                                            "count": 195002,
                                                             "is_parallel": true,
-                                                            "self": 21.00333142396846,
+                                                            "self": 67.04157252854793,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 70.41699403704462,
-                                                                    "count": 505336,
+                                                                    "total": 236.02446295541313,
+                                                                    "count": 1560016,
                                                                     "is_parallel": true,
-                                                                    "self": 70.41699403704462
+                                                                    "self": 236.02446295541313
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 668.5328141390328,
-                            "count": 63168,
-                            "self": 2.1626669000211223,
+                            "total": 1979.3958058989888,
+                            "count": 195003,
+                            "self": 7.312480344824053,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 144.03398588901132,
-                                    "count": 63168,
-                                    "self": 143.82997110501105,
+                                    "total": 437.3572831341439,
+                                    "count": 195003,
+                                    "self": 436.78805104514277,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.20401478400026463,
-                                            "count": 2,
-                                            "self": 0.20401478400026463
+                                            "total": 0.5692320890011615,
+                                            "count": 6,
+                                            "self": 0.5692320890011615
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 522.3361613500003,
-                                    "count": 445,
-                                    "self": 202.14452847800897,
+                                    "total": 1534.7260424200208,
+                                    "count": 1386,
+                                    "self": 584.1678885040551,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 320.1916328719914,
-                                            "count": 22761,
-                                            "self": 320.1916328719914
+                                            "total": 950.5581539159657,
+                                            "count": 68400,
+                                            "self": 950.5581539159657
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.890000001178123e-07,
+                    "total": 1.0040002962341532e-06,
                     "count": 1,
-                    "self": 9.890000001178123e-07
+                    "self": 1.0040002962341532e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09259095299967157,
+                    "total": 0.08703724599945417,
                     "count": 1,
-                    "self": 0.0014868029998069687,
+                    "self": 0.0017129400002886541,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0911041499998646,
+                            "total": 0.08532430599916552,
                             "count": 1,
-                            "self": 0.0911041499998646
+                            "self": 0.08532430599916552
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499993,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499993.onnx",
-                "reward": -0.9992000460624695,
-                "creation_time": 1673866183.0152473,
+                "steps": 1499994,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499994.onnx",
+                "reward": 1.7707999676465989,
+                "creation_time": 1673871022.1623971,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499993.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499994.pt"
                 ]
             },
             {
-                "steps": 999955,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999955.onnx",
-                "reward": 0.8245999366044998,
-                "creation_time": 1673867202.180884,
+                "steps": 1999965,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999965.onnx",
+                "reward": 1.7389999851584435,
+                "creation_time": 1673872217.1726336,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999955.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1999965.pt"
                 ]
             },
             {
-                "steps": 1000083,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000083.onnx",
-                "reward": 0.8245999366044998,
-                "creation_time": 1673867202.28807,
+                "steps": 2499926,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499926.onnx",
+                "reward": 1.8069999366998672,
+                "creation_time": 1673873421.5577404,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000083.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-2499926.pt"
+                ]
+            },
+            {
+                "steps": 2999926,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999926.onnx",
+                "reward": 1.7581817981871692,
+                "creation_time": 1673874671.5197527,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999926.pt"
+                ]
+            },
+            {
+                "steps": 3000054,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000054.onnx",
+                "reward": 1.7581817981871692,
+                "creation_time": 1673874671.6201792,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000054.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000083,
+            "steps": 3000054,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 0.8245999366044998,
-            "creation_time": 1673867202.28807,
+            "reward": 1.7581817981871692,
+            "creation_time": 1673874671.6201792,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000083.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-3000054.pt"
             ]
         }
     },