Learning Rate 0.0005

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad80fdf942675ea8dc67fd75af5b951bcbcf765a930ba7b3881fa07bdf8d5e09
+oid sha256:2bb51b3d8db03d749c716ac706849d514bcabbfa484e52b110207486534c4faf
 size 1420238

Pyramids/Pyramids-1000053.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb51b3d8db03d749c716ac706849d514bcabbfa484e52b110207486534c4faf
+size 1420238

Pyramids/Pyramids-1000053.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4e66cbe99b499c03c225b1d59eb10de47d6cd9a98a6c9a1d4b001d059837a21
+size 8656252

Pyramids/Pyramids-499960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1522d014a86e7a56e4f3bb05fb08e4a1e50ada08bf70c5199024b82be194bc0
+size 1420238

Pyramids/Pyramids-499960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8f776973694b0b3122dbda3e332ea7f131bdb0efb53633ed1b1d381b654bb6
+size 8656173

Pyramids/Pyramids-999925.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb51b3d8db03d749c716ac706849d514bcabbfa484e52b110207486534c4faf
+size 1420238

Pyramids/Pyramids-999925.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014d329531fd87317f091719be49869c8452e2e15d218f9f17db517c46b46909
+size 8656173

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daa62a1c47d32494cea3f496936bbb80a374fc58f2a74ae073534fc9dd7529ed
+oid sha256:6f01f6d746817702393a3c24d2225081038813eece8004ccbda23bd44f00b02d
 size 8655778

Pyramids/events.out.tfevents.1716488049.a8ae1f813db6.4085.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bda6749c2781838bd0cb281c8079db8f84eec304895d8e022e2e0d0e5e07a45
+size 332998

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0005, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training 3", "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": 0.0005, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training 3", "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 3000000
+    max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false

run_logs/Player-0.log

@@ -1,12 +1,9 @@
 Mono path[0] = '/content/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/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] 55355 [Flags] 2 [Guid] 1799805569 [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] 55263 [Flags] 2 [Guid] 2994701475 [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/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.151 seconds
+- Completed reload, in  0.091 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: 0.842078 ms
+UnloadTime: 0.803401 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]: 134 frames, [32.0 KB-64.0 KB]: 298 frames, [64.0 KB-128.0 KB]: 4 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 7210 frames, [32.0 KB-64.0 KB]: 9068 frames, [64.0 KB-128.0 KB]: 2492 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 480 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -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]: 138 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.5 MB
+  Peak Allocated memory 1.6 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11788
+  Peak main deferred allocation count 12318
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 436 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames, [32.0 MB-64.0 MB]: 2 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 25.6 MB
+      Peak Block count 3
+      Peak Allocated memory 32.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 437 frames
+      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 23.6 MB
+      Peak Allocated memory 20.7 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -257,13 +254,13 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 436 frames, [64.0 KB-128.0 KB]: 1 frames
+      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
       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]: 437 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -275,16 +272,16 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 138 frames
+      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
       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]: 436 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 3.9 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,25 +290,25 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 437 frames
+      Peak usage frame count: [0-1.0 KB]: 18771 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]: 437 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18771 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]: 437 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18771 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.6 KB
+  Peak Allocated memory 29.2 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1716487980502,"processId":3562,"allocatedMemory":1970103,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3417},{"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":1716490331085,"processId":4121,"allocatedMemory":1970103,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3417},{"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

@@ -1,8 +1,190 @@
 {
     "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.3222525119781494,
+            "min": 0.3222525119781494,
+            "max": 1.4659395217895508,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 9760.3837890625,
+            "min": 9760.3837890625,
+            "max": 44470.7421875,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989958.0,
+            "min": 29891.0,
+            "max": 989958.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989958.0,
+            "min": 29891.0,
+            "max": 989958.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.47749483585357666,
+            "min": -0.08871790766716003,
+            "max": 0.5511891841888428,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 132.2660675048828,
+            "min": -21.38101577758789,
+            "max": 151.5770263671875,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.015047059394419193,
+            "min": -0.005299135576933622,
+            "max": 0.17912089824676514,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.168035507202148,
+            "min": -1.3671770095825195,
+            "max": 43.34725570678711,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06320590491287431,
+            "min": 0.06320590491287431,
+            "max": 0.0730630686803863,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.8848826687802404,
+            "min": 0.4968184159453771,
+            "max": 1.0756079281586697,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01575721711283439,
+            "min": 0.0007021169247567058,
+            "max": 0.017605286438733207,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.22060103957968147,
+            "min": 0.00982963694659388,
+            "max": 0.2464740101422649,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.2711918886207147e-05,
+            "min": 1.2711918886207147e-05,
+            "max": 0.0004919177159021714,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00017796686440690006,
+            "min": 0.00017796686440690006,
+            "max": 0.005845270230946,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1025423642857143,
+            "min": 0.1025423642857143,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4355931000000002,
+            "min": 1.3886848,
+            "max": 2.569054,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026398219214285735,
+            "min": 0.00026398219214285735,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0036957506900000027,
+            "min": 0.0036957506900000027,
+            "max": 0.1169284946,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011278084479272366,
+            "min": 0.011144990101456642,
+            "max": 0.36744362115859985,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.15789318084716797,
+            "min": 0.1560298651456833,
+            "max": 2.5721054077148438,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 367.3690476190476,
+            "min": 341.2528735632184,
+            "max": 997.1612903225806,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30859.0,
+            "min": 16818.0,
+            "max": 33588.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5616553960794426,
+            "min": -0.9298000508739103,
+            "max": 1.6587470978841015,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 129.61739787459373,
+            "min": -28.823801577091217,
+            "max": 144.31099751591682,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5616553960794426,
+            "min": -0.9298000508739103,
+            "max": 1.6587470978841015,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 129.61739787459373,
+            "min": -28.823801577091217,
+            "max": 144.31099751591682,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.043077289802162536,
+            "min": 0.040856167263600265,
+            "max": 6.9591685182908005,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.5754150535794906,
+            "min": 3.4271382787119364,
+            "max": 118.3058648109436,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1716487933",
+        "start_time_seconds": "1716488048",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/MyP.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training 3 --no-graphics",
         "mlagents_version": "1.1.0.dev0",
@@ -10,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.3.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1716487980"
+        "end_time_seconds": "1716490331"
     },
-    "total": 46.65557004799996,
+    "total": 2282.311435854,
     "count": 1,
-    "self": 0.20746911799994905,
+    "self": 0.4786486870002591,
     "children": {
         "run_training.setup": {
-            "total": 0.08246326200003296,
+            "total": 0.0551037620000443,
             "count": 1,
-            "self": 0.08246326200003296
+            "self": 0.0551037620000443
         },
         "TrainerController.start_learning": {
-            "total": 46.36563766799998,
+            "total": 2281.777683405,
             "count": 1,
-            "self": 0.031194542001458103,
+            "self": 1.6003637430912931,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.134752148000075,
+                    "total": 2.2616075240000555,
                     "count": 1,
-                    "self": 3.134752148000075
+                    "self": 2.2616075240000555
                 },
                 "TrainerController.advance": {
-                    "total": 42.922486348998405,
-                    "count": 1455,
-                    "self": 0.031827385999008584,
+                    "total": 2277.8291122499086,
+                    "count": 63631,
+                    "self": 1.5559853428994757,
                     "children": {
                         "env_step": {
-                            "total": 27.5773388690003,
-                            "count": 1455,
-                            "self": 23.865058616998795,
+                            "total": 1632.1043965199906,
+                            "count": 63631,
+                            "self": 1486.8170469949891,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 3.6940333239996335,
-                                    "count": 1455,
-                                    "self": 0.11247966500127404,
+                                    "total": 144.32940367303684,
+                                    "count": 63631,
+                                    "self": 5.127661076062623,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 3.5815536589983594,
-                                            "count": 1455,
-                                            "self": 3.5815536589983594
+                                            "total": 139.2017425969742,
+                                            "count": 62569,
+                                            "self": 139.2017425969742
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.01824692800187222,
-                                    "count": 1454,
+                                    "total": 0.9579458519647233,
+                                    "count": 63631,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 46.062112203001675,
-                                            "count": 1454,
+                                            "total": 2276.0044967260137,
+                                            "count": 63631,
                                             "is_parallel": true,
-                                            "self": 25.046004620005533,
+                                            "self": 923.1175827560146,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.005040962999942167,
+                                                            "total": 0.003181730000051175,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.003572204000079182,
+                                                            "self": 0.0007837570001356653,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014687589998629846,
+                                                                    "total": 0.0023979729999155097,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014687589998629846
+                                                                    "self": 0.0023979729999155097
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05415789899996071,
+                                                            "total": 0.0492832699999326,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006511240001145779,
+                                                            "self": 0.0006623609998541724,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005108719999498135,
+                                                                    "total": 0.0004279930000166132,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005108719999498135
+                                                                    "self": 0.0004279930000166132
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05122314899995217,
+                                                                    "total": 0.046442454000043654,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05122314899995217
+                                                                    "self": 0.046442454000043654
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017727539999441433,
+                                                                    "total": 0.0017504620000181603,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00037944999985484174,
+                                                                    "self": 0.0003583980002304088,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013933040000893016,
+                                                                            "total": 0.0013920639997877515,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013933040000893016
+                                                                            "self": 0.0013920639997877515
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 21.016107582996142,
-                                                    "count": 1453,
+                                                    "total": 1352.8869139699991,
+                                                    "count": 63630,
                                                     "is_parallel": true,
-                                                    "self": 0.8104601809982341,
+                                                    "self": 35.446781508947424,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.5991248779995431,
-                                                            "count": 1453,
+                                                            "total": 24.573737161966392,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 0.5991248779995431
+                                                            "self": 24.573737161966392
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 17.21316551799839,
-                                                            "count": 1453,
+                                                            "total": 1186.9653988400887,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 17.21316551799839
+                                                            "self": 1186.9653988400887
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 2.393357005999974,
-                                                            "count": 1453,
+                                                            "total": 105.90099645899659,
+                                                            "count": 63630,
                                                             "is_parallel": true,
-                                                            "self": 0.4744283800022231,
+                                                            "self": 22.42560795598922,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.9189286259977507,
-                                                                    "count": 11624,
+                                                                    "total": 83.47538850300737,
+                                                                    "count": 509040,
                                                                     "is_parallel": true,
-                                                                    "self": 1.9189286259977507
+                                                                    "self": 83.47538850300737
                                                                 }
                                                             }
                                                         }
@@ -161,24 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 15.313320093999096,
-                            "count": 1454,
-                            "self": 0.03751292199774525,
+                            "total": 644.1687303870183,
+                            "count": 63631,
+                            "self": 2.8938029910010528,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 2.311935829001527,
-                                    "count": 1454,
-                                    "self": 2.311935829001527
+                                    "total": 136.67017558201405,
+                                    "count": 63631,
+                                    "self": 136.47288772401407,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.1972878579999815,
+                                            "count": 2,
+                                            "self": 0.1972878579999815
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 12.963871342999823,
-                                    "count": 5,
-                                    "self": 7.133931484997788,
+                                    "total": 504.6047518140032,
+                                    "count": 453,
+                                    "self": 298.2204146029999,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 5.829939858002035,
-                                            "count": 471,
-                                            "self": 5.829939858002035
+                                            "total": 206.3843372110033,
+                                            "count": 22767,
+                                            "self": 206.3843372110033
                                         }
                                     }
                                 }
@@ -187,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.620000034563418e-06,
+                    "total": 1.3409999155555852e-06,
                     "count": 1,
-                    "self": 1.620000034563418e-06
+                    "self": 1.3409999155555852e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.2772030090000044,
+                    "total": 0.08659854699999414,
                     "count": 1,
-                    "self": 0.002090769000005821,
+                    "self": 0.0013089630001559271,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.27511223999999856,
+                            "total": 0.08528958399983821,
                             "count": 1,
-                            "self": 0.27511223999999856
+                            "self": 0.08528958399983821
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 22144,
-                "file_path": "results/Pyramids Training 3/Pyramids/Pyramids-22144.onnx",
-                "reward": null,
-                "creation_time": 1716487980.3687215,
+                "steps": 499960,
+                "file_path": "results/Pyramids Training 3/Pyramids/Pyramids-499960.onnx",
+                "reward": -1.0000000521540642,
+                "creation_time": 1716489116.7850225,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training 3/Pyramids/Pyramids-22144.pt"
+                    "results/Pyramids Training 3/Pyramids/Pyramids-499960.pt"
+                ]
+            },
+            {
+                "steps": 999925,
+                "file_path": "results/Pyramids Training 3/Pyramids/Pyramids-999925.onnx",
+                "reward": 1.7526666571696599,
+                "creation_time": 1716490330.5576794,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 3/Pyramids/Pyramids-999925.pt"
+                ]
+            },
+            {
+                "steps": 1000053,
+                "file_path": "results/Pyramids Training 3/Pyramids/Pyramids-1000053.onnx",
+                "reward": 1.7526666571696599,
+                "creation_time": 1716490330.656274,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training 3/Pyramids/Pyramids-1000053.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 22144,
+            "steps": 1000053,
             "file_path": "results/Pyramids Training 3/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1716487980.3687215,
+            "reward": 1.7526666571696599,
+            "creation_time": 1716490330.656274,
             "auxillary_file_paths": [
-                "results/Pyramids Training 3/Pyramids/Pyramids-22144.pt"
+                "results/Pyramids Training 3/Pyramids/Pyramids-1000053.pt"
             ]
         }
     },