Second time

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375e0de80e8c2f1bb70f4fc910275efef155f20a02a9d1c15ad3ec7b61c35161
+oid sha256:46788013940627101a3cb7e6a8a2be5f818a9e38d7609e07699c2e13ddc1a6aa
 size 1417437

Pyramids/{Pyramids-1000007.onnx → Pyramids-1000111.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375e0de80e8c2f1bb70f4fc910275efef155f20a02a9d1c15ad3ec7b61c35161
+oid sha256:46788013940627101a3cb7e6a8a2be5f818a9e38d7609e07699c2e13ddc1a6aa
 size 1417437

Pyramids/{Pyramids-1000007.pt → Pyramids-1000111.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f97f4758a144b19a6a4f13d2f5717299ebe8dfd63853b25eba323feb3c29dae
-size 8652382
+oid sha256:bd4c7c6c77e9b0488bb4d4b815141610b8ed7b9e8af364b0c7c8fa392b47d4c2
+size 8652354

Pyramids/{Pyramids-999879.onnx → Pyramids-499989.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:375e0de80e8c2f1bb70f4fc910275efef155f20a02a9d1c15ad3ec7b61c35161
+oid sha256:a93542598cf44bdcd32296d686cec1166a86b35a95d48a5ffc94f6b4ba0d7141
 size 1417437

Pyramids/{Pyramids-499946.pt → Pyramids-499989.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b79fc92e09f679d33f85401ce0adcb3364479c24f737f5888d3a4783cb724a40
-size 8652382
+oid sha256:bc04f4013b75fa20e4c51734c26bfd7c166b9fd488b8d548e8b9432ba09c5da4
+size 8652354

Pyramids/Pyramids-999879.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4cc18b80fe27509f71b56e3ce10ea71b8f79f9beba452ab97f0b077856a7f6e1
-size 8652382

Pyramids/{Pyramids-499946.onnx → Pyramids-999983.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7ac27cedd6df9e6c39f0dd28f146051dfbf3f58cd85413a59ce589eb13bf15
+oid sha256:46788013940627101a3cb7e6a8a2be5f818a9e38d7609e07699c2e13ddc1a6aa
 size 1417437

Pyramids/Pyramids-999983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b135da1902ca1df7295c494bee0439221396cd76b05e9710873fafa3cf3fde
+size 8652354

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f97f4758a144b19a6a4f13d2f5717299ebe8dfd63853b25eba323feb3c29dae
-size 8652382
+oid sha256:bd4c7c6c77e9b0488bb4d4b815141610b8ed7b9e8af364b0c7c8fa392b47d4c2
+size 8652354

Pyramids/{events.out.tfevents.1674418225.f73c5876ef7a.18271.0 → events.out.tfevents.1674421873.f73c5876ef7a.33273.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f656160f821f5440e68ab46c59769e76873f52e997bec330808158a3c7d378fb
-size 342359
+oid sha256:93e7cd0441da559cae59613c15d6e5108da03e0503aa6add61a8647db7b0824d
+size 332962

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": 0.98, "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 Training2", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -34,7 +34,7 @@ behaviors:
           goal_conditioning_type: hyper
           deterministic: false
       rnd:
-        gamma: 0.99
+        gamma: 0.98
         strength: 0.01
         network_settings:
           normalize: false
@@ -75,7 +75,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training2
   initialize_from: null
   load_model: false
   resume: false

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) 172.28.0.12
-Multi-casting "[IP] 172.28.0.12 [Port] 55407 [Flags] 2 [Guid] 2900623614 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.12 [Port] 55116 [Flags] 2 [Guid] 4253888430 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-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:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.080 seconds
+- Completed reload, in  0.079 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: 0.726329 ms
+UnloadTime: 0.728298 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]: 1495 frames, [32.0 KB-64.0 KB]: 14550 frames, [64.0 KB-128.0 KB]: 2725 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4770 frames, [32.0 KB-64.0 KB]: 11628 frames, [64.0 KB-128.0 KB]: 2372 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
@@ -213,22 +210,22 @@ PlayerConnection::CleanupMemory Statistics:
   Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12989
+  Peak main deferred allocation count 11320
     [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]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.8 MB
+      Peak Allocated memory 31.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
       Peak usage frame count: [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 22.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,7 +252,7 @@ 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
       Requested Block Size 16.0 MB
@@ -273,7 +270,7 @@ 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
       Requested Block Size 4.0 MB
@@ -291,7 +288,7 @@ 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
       Requested Block Size 2.0 MB
@@ -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":1674420181755,"processId":18292,"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":1674423853299,"processId":33294,"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

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.5169119238853455,
-            "min": 0.5169119238853455,
-            "max": 1.3073537349700928,
+            "value": 0.31421124935150146,
+            "min": 0.2840237617492676,
+            "max": 1.3432326316833496,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 15441.1923828125,
-            "min": 15441.1923828125,
-            "max": 39659.8828125,
+            "value": 9431.365234375,
+            "min": 8525.2568359375,
+            "max": 40748.3046875,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989989.0,
-            "min": 29980.0,
-            "max": 989989.0,
+            "value": 989908.0,
+            "min": 29952.0,
+            "max": 989908.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989989.0,
-            "min": 29980.0,
-            "max": 989989.0,
+            "value": 989908.0,
+            "min": 29952.0,
+            "max": 989908.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3589520752429962,
-            "min": -0.10609453171491623,
-            "max": 0.4193597733974457,
+            "value": 0.28630736470222473,
+            "min": -0.10326258093118668,
+            "max": 0.3394848704338074,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 96.19915771484375,
-            "min": -25.462688446044922,
-            "max": 114.06585693359375,
+            "value": 73.86730194091797,
+            "min": -24.886281967163086,
+            "max": 86.90812683105469,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.03227285295724869,
-            "min": -0.011950272135436535,
-            "max": 0.4846712648868561,
+            "value": 0.002211504615843296,
+            "min": -0.003026550868526101,
+            "max": 0.19428789615631104,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 8.649124145507812,
-            "min": -3.250473976135254,
-            "max": 115.35176086425781,
+            "value": 0.5705682039260864,
+            "min": -0.753611147403717,
+            "max": 46.04623031616211,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06635625898239336,
-            "min": 0.06579637175146426,
-            "max": 0.07496118016013711,
+            "value": 0.06974054059003071,
+            "min": 0.06547258155443982,
+            "max": 0.07400301405891577,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.928987625753507,
-            "min": 0.5335781675934241,
-            "max": 1.0839560226589788,
+            "value": 1.0461081088504607,
+            "min": 0.4902440781697387,
+            "max": 1.0932508326813524,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.013335079653881535,
-            "min": 0.0010710213334948618,
-            "max": 0.01573796351989718,
+            "value": 0.010319827537303808,
+            "min": 0.0010141509631897306,
+            "max": 0.011688448390607186,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1866911151543415,
-            "min": 0.012852256001938341,
-            "max": 0.22033148927856053,
+            "value": 0.1547974130595571,
+            "min": 0.013114335913794281,
+            "max": 0.16533768097410667,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.618511746242856e-06,
-            "min": 7.618511746242856e-06,
-            "max": 0.00029484975171675,
+            "value": 7.47305750901333e-06,
+            "min": 7.47305750901333e-06,
+            "max": 0.00029515063018788575,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010665916444739999,
-            "min": 0.00010665916444739999,
-            "max": 0.0036335566888144994,
+            "value": 0.00011209586263519996,
+            "min": 0.00011209586263519996,
+            "max": 0.003633732788755799,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10253947142857144,
-            "min": 0.10253947142857144,
-            "max": 0.19828325,
+            "value": 0.10249098666666664,
+            "min": 0.10249098666666664,
+            "max": 0.19838354285714285,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4355526,
-            "min": 1.4355526,
-            "max": 2.6111855000000004,
+            "value": 1.5373647999999998,
+            "min": 1.371456,
+            "max": 2.6112442000000007,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026369319571428577,
-            "min": 0.00026369319571428577,
-            "max": 0.009828496675,
+            "value": 0.00025884956799999997,
+            "min": 0.00025884956799999997,
+            "max": 0.00983851593142857,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036917047400000006,
-            "min": 0.0036917047400000006,
-            "max": 0.12113743144999999,
+            "value": 0.0038827435199999994,
+            "min": 0.0038827435199999994,
+            "max": 0.12114329557999999,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00866986159235239,
-            "min": 0.00866986159235239,
-            "max": 0.5435911417007446,
+            "value": 0.010354802943766117,
+            "min": 0.010210125707089901,
+            "max": 0.45836424827575684,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12137806415557861,
-            "min": 0.12137806415557861,
-            "max": 4.348729133605957,
+            "value": 0.15532204508781433,
+            "min": 0.132731631398201,
+            "max": 3.208549737930298,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 440.5571428571429,
-            "min": 422.02777777777777,
-            "max": 995.71875,
+            "value": 525.5192307692307,
+            "min": 495.7049180327869,
+            "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30839.0,
-            "min": 16650.0,
-            "max": 33042.0,
+            "value": 27327.0,
+            "min": 15984.0,
+            "max": 33967.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3307799742690154,
-            "min": -0.9341500529553741,
-            "max": 1.3556777554460697,
+            "value": 1.0897307371577392,
+            "min": -1.0000000521540642,
+            "max": 1.1325817946683276,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 93.15459819883108,
-            "min": -29.892801694571972,
-            "max": 97.60879839211702,
+            "value": 56.665998332202435,
+            "min": -29.099601708352566,
+            "max": 67.75399824976921,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3307799742690154,
-            "min": -0.9341500529553741,
-            "max": 1.3556777554460697,
+            "value": 1.0897307371577392,
+            "min": -1.0000000521540642,
+            "max": 1.1325817946683276,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 93.15459819883108,
-            "min": -29.892801694571972,
-            "max": 97.60879839211702,
+            "value": 56.665998332202435,
+            "min": -29.099601708352566,
+            "max": 67.75399824976921,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.039998169381786804,
-            "min": 0.03832940760488176,
-            "max": 11.33438495794932,
+            "value": 0.056008590235321135,
+            "min": 0.056008590235321135,
+            "max": 8.996327891945839,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.799871856725076,
-            "min": 2.7597173475514865,
-            "max": 204.01892924308777,
+            "value": 2.912446692236699,
+            "min": 2.912446692236699,
+            "max": 143.94124627113342,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,74 +184,74 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1674418222",
+        "start_time_seconds": "1674421870",
         "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training2 --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": "1674420181"
+        "end_time_seconds": "1674423853"
     },
-    "total": 1958.951682592,
+    "total": 1983.170290858,
     "count": 1,
-    "self": 0.42629265100003977,
+    "self": 0.4334071639996182,
     "children": {
         "run_training.setup": {
-            "total": 0.10293960899980448,
+            "total": 0.10060317799980112,
             "count": 1,
-            "self": 0.10293960899980448
+            "self": 0.10060317799980112
         },
         "TrainerController.start_learning": {
-            "total": 1958.4224503320002,
+            "total": 1982.6362805160006,
             "count": 1,
-            "self": 1.1347517761678318,
+            "self": 1.353520445984941,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 5.989304759999868,
+                    "total": 5.930512423999971,
                     "count": 1,
-                    "self": 5.989304759999868
+                    "self": 5.930512423999971
                 },
                 "TrainerController.advance": {
-                    "total": 1951.2169138228328,
-                    "count": 63606,
-                    "self": 1.2237890878641338,
+                    "total": 1975.2708701840156,
+                    "count": 63585,
+                    "self": 1.3766213879198403,
                     "children": {
                         "env_step": {
-                            "total": 1312.9251238820461,
-                            "count": 63606,
-                            "self": 1210.4891112990072,
+                            "total": 1327.3217640259427,
+                            "count": 63585,
+                            "self": 1217.1686995927785,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 101.71212524004659,
-                                    "count": 63606,
-                                    "self": 4.385736698061919,
+                                    "total": 109.33425272204022,
+                                    "count": 63585,
+                                    "self": 4.618678569950134,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 97.32638854198467,
+                                            "total": 104.71557415209008,
                                             "count": 62570,
-                                            "self": 32.59449646198118,
+                                            "self": 35.004307358019105,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 64.73189208000349,
+                                                    "total": 69.71126679407098,
                                                     "count": 62570,
-                                                    "self": 64.73189208000349
+                                                    "self": 69.71126679407098
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7238873429923842,
-                                    "count": 63606,
+                                    "total": 0.818811711123999,
+                                    "count": 63585,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 1954.2095819389142,
-                                            "count": 63606,
+                                            "total": 1977.8371454249473,
+                                            "count": 63585,
                                             "is_parallel": true,
-                                            "self": 840.0561010508136,
+                                            "self": 863.7658797191134,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0021525120000660536,
+                                                            "total": 0.002054730999589083,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007887900010246085,
+                                                            "self": 0.0007944589970065863,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001363721999041445,
+                                                                    "total": 0.0012602720025824965,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001363721999041445
+                                                                    "self": 0.0012602720025824965
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.045942916000058176,
+                                                            "total": 0.048239406999528,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005090849999760394,
+                                                            "self": 0.0004901860002064495,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004749350000565755,
+                                                                    "total": 0.00045722699996986194,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004749350000565755
+                                                                    "self": 0.00045722699996986194
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.043164431000150216,
+                                                                    "total": 0.045628173999830324,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.043164431000150216
+                                                                    "self": 0.045628173999830324
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017944649998753448,
+                                                                    "total": 0.0016638199995213654,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004509650016188971,
+                                                                    "self": 0.0004661449993363931,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013434999982564477,
+                                                                            "total": 0.0011976750001849723,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013434999982564477
+                                                                            "self": 0.0011976750001849723
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1114.1534808881006,
-                                                    "count": 63605,
+                                                    "total": 1114.0712657058339,
+                                                    "count": 63584,
                                                     "is_parallel": true,
-                                                    "self": 27.019050720966334,
+                                                    "self": 28.284180096286946,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.044856184942546,
-                                                            "count": 63605,
+                                                            "total": 23.93000472285894,
+                                                            "count": 63584,
                                                             "is_parallel": true,
-                                                            "self": 23.044856184942546
+                                                            "self": 23.93000472285894
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 963.2631649760033,
-                                                            "count": 63605,
+                                                            "total": 956.1459612529579,
+                                                            "count": 63584,
                                                             "is_parallel": true,
-                                                            "self": 963.2631649760033
+                                                            "self": 956.1459612529579
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 100.82640900618844,
-                                                            "count": 63605,
+                                                            "total": 105.71111963373005,
+                                                            "count": 63584,
                                                             "is_parallel": true,
-                                                            "self": 22.094549035230557,
+                                                            "self": 23.549288799286842,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 78.73185997095788,
-                                                                    "count": 508840,
+                                                                    "total": 82.16183083444321,
+                                                                    "count": 508672,
                                                                     "is_parallel": true,
-                                                                    "self": 78.73185997095788
+                                                                    "self": 82.16183083444321
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 637.0680008529225,
-                            "count": 63606,
-                            "self": 2.242945856926781,
+                            "total": 646.5724847701531,
+                            "count": 63585,
+                            "self": 2.5010763138561742,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 144.45091875599883,
-                                    "count": 63606,
-                                    "self": 144.24995177599885,
+                                    "total": 150.38760613227169,
+                                    "count": 63585,
+                                    "self": 150.19726568227088,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2009669799999756,
+                                            "total": 0.19034045000080368,
                                             "count": 2,
-                                            "self": 0.2009669799999756
+                                            "self": 0.19034045000080368
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 490.3741362399969,
-                                    "count": 455,
-                                    "self": 184.62454752995836,
+                                    "total": 493.68380232402524,
+                                    "count": 453,
+                                    "self": 183.87012862614483,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 305.74958871003855,
-                                            "count": 22782,
-                                            "self": 305.74958871003855
+                                            "total": 309.8136736978804,
+                                            "count": 22758,
+                                            "self": 309.8136736978804
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.79000105871819e-07,
+                    "total": 9.640007192501798e-07,
                     "count": 1,
-                    "self": 9.79000105871819e-07
+                    "self": 9.640007192501798e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.0814789939995535,
+                    "total": 0.08137649799937208,
                     "count": 1,
-                    "self": 0.0013771670001005987,
+                    "self": 0.001334700998995686,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.0801018269994529,
+                            "total": 0.08004179700037639,
                             "count": 1,
-                            "self": 0.0801018269994529
+                            "self": 0.08004179700037639
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499946,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499946.onnx",
-                "reward": 1.6246666461229324,
-                "creation_time": 1674419154.5548272,
+                "steps": 499989,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-499989.onnx",
+                "reward": 0.07259994745254517,
+                "creation_time": 1674422823.8779445,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499946.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-499989.pt"
                 ]
             },
             {
-                "steps": 999879,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999879.onnx",
-                "reward": 1.5129999443888664,
-                "creation_time": 1674420181.2846541,
+                "steps": 999983,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-999983.onnx",
+                "reward": 1.6389999687671661,
+                "creation_time": 1674423852.8117085,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999879.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-999983.pt"
                 ]
             },
             {
-                "steps": 1000007,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000007.onnx",
-                "reward": 1.5129999443888664,
-                "creation_time": 1674420181.3795576,
+                "steps": 1000111,
+                "file_path": "results/Pyramids Training2/Pyramids/Pyramids-1000111.onnx",
+                "reward": 1.6389999687671661,
+                "creation_time": 1674423852.9078035,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000007.pt"
+                    "results/Pyramids Training2/Pyramids/Pyramids-1000111.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000007,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.5129999443888664,
-            "creation_time": 1674420181.3795576,
+            "steps": 1000111,
+            "file_path": "results/Pyramids Training2/Pyramids.onnx",
+            "reward": 1.6389999687671661,
+            "creation_time": 1674423852.9078035,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000007.pt"
+                "results/Pyramids Training2/Pyramids/Pyramids-1000111.pt"
             ]
         }
     },