First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1597440a89f0d7ff6befb5d9eb07f7010579ff7fbd2dd9374ba2ffb0e05b57
+oid sha256:0ca168076d9a1788199e463ef3e8ac23cc2a662e917ed91f06193bdde983d7af
 size 1420238

Pyramids/Pyramids-1000007.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca168076d9a1788199e463ef3e8ac23cc2a662e917ed91f06193bdde983d7af
+size 1420238

Pyramids/Pyramids-1000007.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551f8a50fd880dc145afe2ef0b52e617b69f13d545a23dc804bfd63c41bbc370
+size 8656731

Pyramids/Pyramids-499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e60e16f9efcf54cdc16f041b1c6a57ea27186f74a71fe64e281df6a90af2a57
+size 1420238

Pyramids/Pyramids-499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbfc03c3af33fa823710636130d37c5a2b39c15c7b2ff2787f88f576f5101cb
+size 8656650

Pyramids/Pyramids-999879.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca168076d9a1788199e463ef3e8ac23cc2a662e917ed91f06193bdde983d7af
+size 1420238

Pyramids/Pyramids-999879.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4f00908a6a575ccb02203625648d5f4799cf51def21f311415ef3ccca37078
+size 8656650

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ecae301ccf37fc7f8899aa767cf0221d9b45002481918bbd4ab7a54f3954b31
+oid sha256:86ed8be78cbad27876adde424acade3f3661cc40294c14705389124b0c8015aa
 size 8656181

Pyramids/events.out.tfevents.1749443560.ad118fea1525.32366.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25d7d0b62ddf4bff9a2bbf42aa9eafa23b01916922a8707cf823e4aefe8fe871
+size 313786

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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", "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": 4096, "learning_rate": 0.0002, "beta": 0.005, "epsilon": 0.1, "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_2", "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

@@ -4,10 +4,10 @@ behaviors:
     trainer_type: ppo
     hyperparameters:
       batch_size: 128
-      buffer_size: 2048
-      learning_rate: 0.0003
-      beta: 0.01
-      epsilon: 0.2
+      buffer_size: 4096
+      learning_rate: 0.0002
+      beta: 0.005
+      epsilon: 0.1
       lambd: 0.95
       num_epoch: 3
       shared_critic: false
@@ -79,7 +79,7 @@ engine_settings:
   no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids_Training_2
   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] 55270 [Flags] 2 [Guid] 3797923516 [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] 55509 [Flags] 2 [Guid] 1780557801 [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: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  0.093 seconds
+- Completed reload, in  0.129 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: 0.760925 ms
+UnloadTime: 1.096941 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]: 2400 frames, [32.0 KB-64.0 KB]: 13355 frames, [64.0 KB-128.0 KB]: 3015 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 9240 frames, [32.0 KB-64.0 KB]: 7751 frames, [64.0 KB-128.0 KB]: 1777 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -207,28 +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]: 18470 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 13219
+  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]: 227 frames, [16.0 MB-32.0 MB]: 18544 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18768 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 29.8 MB
+      Peak Allocated memory 30.3 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]: 18769 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.5 MB
+      Peak Allocated memory 23.2 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -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]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18768 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]: 18769 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]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 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]: 18768 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 2
-      Peak Allocated memory 4.7 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 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]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 18769 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]: 18769 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]: 18769 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 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":1749440148112,"processId":8733,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1749445647237,"processId":32383,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3350432217121124,
-            "min": 0.3350432217121124,
-            "max": 1.4906748533248901,
+            "value": 0.6665168404579163,
+            "min": 0.6665168404579163,
+            "max": 1.5946495532989502,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 10110.2646484375,
-            "min": 10110.2646484375,
-            "max": 45221.11328125,
+            "value": 20091.484375,
+            "min": 20091.484375,
+            "max": 48375.2890625,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989970.0,
+            "value": 989954.0,
             "min": 29952.0,
-            "max": 989970.0,
+            "max": 989954.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989970.0,
+            "value": 989954.0,
             "min": 29952.0,
-            "max": 989970.0,
+            "max": 989954.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.5450277924537659,
-            "min": -0.14152459800243378,
-            "max": 0.5970061421394348,
+            "value": 0.18970997631549835,
+            "min": -0.10716152936220169,
+            "max": 0.2471831738948822,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 154.24285888671875,
-            "min": -33.54132843017578,
-            "max": 164.77369689941406,
+            "value": 48.94517517089844,
+            "min": -25.825927734375,
+            "max": 63.278892517089844,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.004259876441210508,
-            "min": -0.13958775997161865,
-            "max": 0.3721037805080414,
+            "value": 0.012041537091135979,
+            "min": 0.006680199410766363,
+            "max": 0.45380517840385437,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -1.2055450677871704,
-            "min": -36.85116958618164,
-            "max": 99.72381591796875,
+            "value": 3.1067166328430176,
+            "min": 1.6566894054412842,
+            "max": 107.55182647705078,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0659075082207675,
-            "min": 0.0659075082207675,
-            "max": 0.07362989712472985,
+            "value": 0.06943605918994374,
+            "min": 0.06585919048631608,
+            "max": 0.07194191388609512,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9227051150907452,
-            "min": 0.4952828431583609,
-            "max": 1.0525541256453534,
+            "value": 0.48605241432960616,
+            "min": 0.2788896204778683,
+            "max": 0.562897801988069,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.017237028111204773,
-            "min": 0.0003032036767087156,
-            "max": 0.02541885567800153,
+            "value": 0.01099524283372808,
+            "min": 0.0001414999053914558,
+            "max": 0.01099524283372808,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2413183935568668,
-            "min": 0.003032036767087156,
-            "max": 0.3558639794920214,
+            "value": 0.07696669983609657,
+            "min": 0.0009904993377401906,
+            "max": 0.08602394675108371,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.685390295378573e-06,
-            "min": 7.685390295378573e-06,
-            "max": 0.00029515063018788575,
+            "value": 5.058011756757141e-06,
+            "min": 5.058011756757141e-06,
+            "max": 0.00019696640151680003,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010759546413530002,
-            "min": 0.00010759546413530002,
-            "max": 0.0030216923927693,
+            "value": 3.540608229729999e-05,
+            "min": 3.540608229729999e-05,
+            "max": 0.0012125400937299997,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.1025617642857143,
-            "min": 0.1025617642857143,
-            "max": 0.19838354285714285,
+            "value": 0.09999999999999999,
+            "min": 0.09999999999999998,
+            "max": 0.1,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4358647000000002,
-            "min": 1.3691136000000002,
-            "max": 2.4826245,
+            "value": 0.7,
+            "min": 0.3999999999999999,
+            "max": 0.8,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002659202521428572,
-            "min": 0.0002659202521428572,
-            "max": 0.00983851593142857,
+            "value": 0.0001361949614285714,
+            "min": 0.0001361949614285714,
+            "max": 0.00492431168,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.003722883530000001,
-            "min": 0.003722883530000001,
-            "max": 0.10075234693,
+            "value": 0.0009533647299999998,
+            "min": 0.0009533647299999998,
+            "max": 0.030322873000000004,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.013633999042212963,
-            "min": 0.013592482544481754,
-            "max": 0.5029053092002869,
+            "value": 0.01803797110915184,
+            "min": 0.01787019893527031,
+            "max": 0.534096896648407,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.19087599217891693,
-            "min": 0.1902947574853897,
-            "max": 3.5203371047973633,
+            "value": 0.12626579403877258,
+            "min": 0.12509138882160187,
+            "max": 2.136387586593628,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 336.75280898876406,
-            "min": 327.34090909090907,
+            "value": 613.4,
+            "min": 601.3877551020408,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29971.0,
+            "value": 30670.0,
             "min": 15984.0,
-            "max": 32457.0,
+            "max": 34234.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.6407707623216543,
+            "value": 0.9464479768276215,
             "min": -1.0000000521540642,
-            "max": 1.6407707623216543,
+            "max": 1.0311673174099045,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 146.02859784662724,
+            "value": 47.32239884138107,
             "min": -32.000001668930054,
-            "max": 146.02859784662724,
+            "max": 50.52719855308533,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.6407707623216543,
+            "value": 0.9464479768276215,
             "min": -1.0000000521540642,
-            "max": 1.6407707623216543,
+            "max": 1.0311673174099045,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 146.02859784662724,
+            "value": 47.32239884138107,
             "min": -32.000001668930054,
-            "max": 146.02859784662724,
+            "max": 50.52719855308533,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.047234541696484535,
-            "min": 0.047234541696484535,
-            "max": 10.46707842964679,
+            "value": 0.11382588352775201,
+            "min": 0.11363009977325493,
+            "max": 12.171295398846269,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 4.203874210987124,
-            "min": 4.203874210987124,
-            "max": 167.47325487434864,
+            "value": 5.691294176387601,
+            "min": 4.879276555497199,
+            "max": 194.7407263815403,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1749437973",
+        "start_time_seconds": "1749443559",
         "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
-        "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_Training_2 --no-graphics",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.7.1+cu126",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1749440148"
+        "end_time_seconds": "1749445647"
     },
-    "total": 2174.268714469,
+    "total": 2087.5942535270005,
     "count": 1,
-    "self": 0.6296457609996651,
+    "self": 0.47591953500068485,
     "children": {
         "run_training.setup": {
-            "total": 0.019719519000091168,
+            "total": 0.020292706999498478,
             "count": 1,
-            "self": 0.019719519000091168
+            "self": 0.020292706999498478
         },
         "TrainerController.start_learning": {
-            "total": 2173.619349189,
+            "total": 2087.0980412850004,
             "count": 1,
-            "self": 1.2442392020211628,
+            "self": 1.2929630827520668,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.2846495490000507,
+                    "total": 3.044654459999947,
                     "count": 1,
-                    "self": 2.2846495490000507
+                    "self": 3.044654459999947
                 },
                 "TrainerController.advance": {
-                    "total": 2170.0112232799797,
-                    "count": 63783,
-                    "self": 1.3635687739993045,
+                    "total": 2082.6721911832474,
+                    "count": 63274,
+                    "self": 1.338734979455694,
                     "children": {
                         "env_step": {
-                            "total": 1498.112009219971,
-                            "count": 63783,
-                            "self": 1352.5979401499433,
+                            "total": 1396.3939620187084,
+                            "count": 63274,
+                            "self": 1246.1081086676086,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 144.78388730404163,
-                                    "count": 63783,
-                                    "self": 4.380544577033106,
+                                    "total": 149.5401656600543,
+                                    "count": 63274,
+                                    "self": 4.545523447043706,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 140.40334272700852,
-                                            "count": 62567,
-                                            "self": 140.40334272700852
+                                            "total": 144.9946422130106,
+                                            "count": 62561,
+                                            "self": 144.9946422130106
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7301817659861172,
-                                    "count": 63783,
+                                    "total": 0.7456876910455321,
+                                    "count": 63274,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2168.87869323307,
-                                            "count": 63783,
+                                            "total": 2082.456540916074,
+                                            "count": 63274,
                                             "is_parallel": true,
-                                            "self": 921.8589489080455,
+                                            "self": 943.1106912942269,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.001907844000015757,
+                                                            "total": 0.002521911999792792,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006393779999598337,
+                                                            "self": 0.0007934859995657462,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0012684660000559234,
+                                                                    "total": 0.0017284260002270457,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0012684660000559234
+                                                                    "self": 0.0017284260002270457
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.06846331400015515,
+                                                            "total": 0.049979223999798705,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005970839997644362,
+                                                            "self": 0.0005230350006968365,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004956710001806641,
+                                                                    "total": 0.0004515149994404055,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004956710001806641
+                                                                    "self": 0.0004515149994404055
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06554277400005049,
+                                                                    "total": 0.047415748000275926,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06554277400005049
+                                                                    "self": 0.047415748000275926
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018277850001595652,
+                                                                    "total": 0.0015889259993855376,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004256940001141629,
+                                                                    "self": 0.00033522400008223485,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0014020910000454023,
+                                                                            "total": 0.0012537019993033027,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0014020910000454023
+                                                                            "self": 0.0012537019993033027
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1247.0197443250245,
-                                                    "count": 63782,
+                                                    "total": 1139.3458496218473,
+                                                    "count": 63273,
                                                     "is_parallel": true,
-                                                    "self": 30.78067624810069,
+                                                    "self": 31.04758551323812,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 22.416148762045395,
-                                                            "count": 63782,
+                                                            "total": 22.727993597838577,
+                                                            "count": 63273,
                                                             "is_parallel": true,
-                                                            "self": 22.416148762045395
+                                                            "self": 22.727993597838577
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1102.1674801959311,
-                                                            "count": 63782,
+                                                            "total": 993.7852744339243,
+                                                            "count": 63273,
                                                             "is_parallel": true,
-                                                            "self": 1102.1674801959311
+                                                            "self": 993.7852744339243
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 91.65543911894724,
-                                                            "count": 63782,
+                                                            "total": 91.78499607684626,
+                                                            "count": 63273,
                                                             "is_parallel": true,
-                                                            "self": 18.04255058982494,
+                                                            "self": 17.978266948128294,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 73.6128885291223,
-                                                                    "count": 510256,
+                                                                    "total": 73.80672912871796,
+                                                                    "count": 506184,
                                                                     "is_parallel": true,
-                                                                    "self": 73.6128885291223
+                                                                    "self": 73.80672912871796
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 670.5356452860096,
-                            "count": 63783,
-                            "self": 2.310295243964447,
+                            "total": 684.9394941850833,
+                            "count": 63274,
+                            "self": 2.440142136817485,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 125.31426553303527,
-                                    "count": 63783,
-                                    "self": 125.11652393003533,
+                                    "total": 125.25541883626374,
+                                    "count": 63274,
+                                    "self": 125.05289813026411,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.19774160299994037,
+                                            "total": 0.2025207059996319,
                                             "count": 2,
-                                            "self": 0.19774160299994037
+                                            "self": 0.2025207059996319
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 542.9110845090099,
-                                    "count": 432,
-                                    "self": 299.69867497199766,
+                                    "total": 557.243933212002,
+                                    "count": 231,
+                                    "self": 307.9904933010275,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 243.21240953701226,
-                                            "count": 22866,
-                                            "self": 243.21240953701226
+                                            "total": 249.25343991097452,
+                                            "count": 23148,
+                                            "self": 249.25343991097452
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.279992809752002e-07,
+                    "total": 8.320002962136641e-07,
                     "count": 1,
-                    "self": 9.279992809752002e-07
+                    "self": 8.320002962136641e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.07923622999987856,
+                    "total": 0.08823172700067516,
                     "count": 1,
-                    "self": 0.0012706739998975536,
+                    "self": 0.0011536390011315234,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.077965555999981,
+                            "total": 0.08707808799954364,
                             "count": 1,
-                            "self": 0.077965555999981
+                            "self": 0.08707808799954364
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,40 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499906,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499906.onnx",
-                "reward": null,
-                "creation_time": 1749438957.5070705,
+                "steps": 499966,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-499966.onnx",
+                "reward": -0.34915005788207054,
+                "creation_time": 1749444565.6293406,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499906.pt"
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-499966.pt"
                 ]
             },
             {
-                "steps": 999996,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999996.onnx",
-                "reward": 1.6094999685883522,
-                "creation_time": 1749440147.462628,
+                "steps": 999879,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-999879.onnx",
+                "reward": 0.24029995501041412,
+                "creation_time": 1749445646.7001588,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999996.pt"
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-999879.pt"
                 ]
             },
             {
-                "steps": 1000124,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000124.onnx",
-                "reward": 1.6094999685883522,
-                "creation_time": 1749440147.5544868,
+                "steps": 1000007,
+                "file_path": "results/Pyramids_Training_2/Pyramids/Pyramids-1000007.onnx",
+                "reward": 0.24029995501041412,
+                "creation_time": 1749445646.799248,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000124.pt"
+                    "results/Pyramids_Training_2/Pyramids/Pyramids-1000007.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000124,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.6094999685883522,
-            "creation_time": 1749440147.5544868,
+            "steps": 1000007,
+            "file_path": "results/Pyramids_Training_2/Pyramids.onnx",
+            "reward": 0.24029995501041412,
+            "creation_time": 1749445646.799248,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000124.pt"
+                "results/Pyramids_Training_2/Pyramids/Pyramids-1000007.pt"
             ]
         }
     },