Third Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52604a75f48f3c7b526cc7ef76eb9b7f3b98876ce196d962bff5b378b84a8941
-size 1420237
+oid sha256:d0adc9192d85ff6a2533fdaf2fea8fe24d9bcd5379782428d8acf7c5f004e1e3
+size 2471803

Pyramids/Pyramids-1000029.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52604a75f48f3c7b526cc7ef76eb9b7f3b98876ce196d962bff5b378b84a8941
-size 1420237
+oid sha256:d0adc9192d85ff6a2533fdaf2fea8fe24d9bcd5379782428d8acf7c5f004e1e3
+size 2471803

Pyramids/Pyramids-1000029.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faffb815e56c418ccc11b59c2099ea10d54736ae469d502c6322f3107e092ef0
-size 8655801
+oid sha256:3e56490ffe555effa9d5705b86e125023cb49def951d20116d4a94de058e32b9
+size 19720601

Pyramids/Pyramids-399945.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95f60779bd96c72cc14497ce0663e92380b878451a7cda2b20d0eb41eb3475b
+size 2471803

Pyramids/Pyramids-399945.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a441473ded67bafbbe41f57c5eafa57035187323f40648eb6ee916d077784ad
+size 19720508

Pyramids/Pyramids-599946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc2b3eb53052f67970bef7091af64ce3908074251e6cbefbdf86632584673c33
+size 2471803

Pyramids/Pyramids-599946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b171dde3d4af9e68ace5363abd484d045be4ce00c798e5cbdc42323b4d98ce59
+size 19720508

Pyramids/Pyramids-799906.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2998a564cfd5c4ec7158f99092c5bd89407d5c45b873526988389a9daa1552ad
+size 2471803

Pyramids/Pyramids-799906.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fada001f764550fa958d7d74de6c1871d46b6911c9fc7d6af37474a693efca4b
+size 19720508

Pyramids/Pyramids-999901.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52604a75f48f3c7b526cc7ef76eb9b7f3b98876ce196d962bff5b378b84a8941
-size 1420237
+oid sha256:d0adc9192d85ff6a2533fdaf2fea8fe24d9bcd5379782428d8acf7c5f004e1e3
+size 2471803

Pyramids/Pyramids-999901.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afa4e8eb2db37acbbbbfcfefccd185e82bc79bb37234ceb82d97d0c34b62100
-size 8655724
+oid sha256:53fe66a93f92655fe77522007af6fbebb17b182b07a52812268610669540e2b2
+size 19720508

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ab0dd99887449acfdf95fc63abab57789485ebbdebf25e8c80c10c4c3de3ff
-size 8655339
+oid sha256:3cf6e9bbf566d5eb29188f2793409833667c6cf003c004469a7d0fed4289f90f
+size 19720043

Pyramids/events.out.tfevents.1697028330.429c7995e803.26013.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293736ff3bf5818d81c7bd0a48bf87c5849e292775da2662dd6d2508cd8c1494
+size 305335

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, "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": 0.001, "epsilon": 0.1, "lambd": 0.9, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "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": 512, "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": true, "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}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training6", "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

@@ -6,19 +6,19 @@ behaviors:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.01
-      epsilon: 0.2
-      lambd: 0.95
+      beta: 0.001
+      epsilon: 0.1
+      lambd: 0.9
       num_epoch: 3
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
-    checkpoint_interval: 500000
+    checkpoint_interval: 200000
     network_settings:
       normalize: false
       hidden_units: 512
-      num_layers: 2
+      num_layers: 3
       vis_encode_type: simple
       memory: null
       goal_conditioning_type: hyper
@@ -40,7 +40,7 @@ behaviors:
         strength: 0.01
         network_settings:
           normalize: false
-          hidden_units: 64
+          hidden_units: 512
           num_layers: 3
           vis_encode_type: simple
           memory: null
@@ -50,7 +50,7 @@ behaviors:
         encoding_size: null
     init_path: null
     keep_checkpoints: 5
-    even_checkpoints: false
+    even_checkpoints: true
     max_steps: 1000000
     time_horizon: 128
     summary_freq: 30000
@@ -63,6 +63,7 @@ env_settings:
   base_port: 5005
   num_envs: 1
   num_areas: 1
+  timeout_wait: 60
   seed: -1
   max_lifetime_restarts: 10
   restarts_rate_limit_n: 1
@@ -77,7 +78,7 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids Training6
   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] 55069 [Flags] 2 [Guid] 1423764548 [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] 55103 [Flags] 2 [Guid] 1664730719 [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  0.141 seconds
+- Completed reload, in  0.088 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: 1.110539 ms
+UnloadTime: 0.747120 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]: 2228 frames, [32.0 KB-64.0 KB]: 14182 frames, [64.0 KB-128.0 KB]: 2358 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2958 frames, [32.0 KB-64.0 KB]: 11615 frames, [64.0 KB-128.0 KB]: 4198 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 2]
+    [ALLOC_TEMP_Background Job.Worker 7]
       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 7]
+    [ALLOC_TEMP_Background Job.Worker 2]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -186,12 +183,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0.8 KB
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 14]
+    [ALLOC_TEMP_Background Job.Worker 9]
       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 9]
+    [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -207,28 +204,28 @@ PlayerConnection::CleanupMemory Statistics:
       Peak Allocated Bytes 128 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 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 12264
+  Peak main deferred allocation count 13352
     [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]: 18768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18771 frames
       Requested Block Size 16.0 MB
       Peak Block count 3
-      Peak Allocated memory 30.5 MB
+      Peak Allocated memory 31.1 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18772 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.4 MB
+      Peak Allocated memory 22.9 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]: 18768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18771 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]: 18769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18772 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]: 18470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18473 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]: 18768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18771 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
-      Peak Allocated memory 4.4 MB
+      Peak Allocated memory 4.7 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TYPETREE] Dual Thread Allocator
   Peak main deferred allocation count 0
@@ -293,19 +290,19 @@ PlayerConnection::CleanupMemory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.7 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18769 frames
+      Peak usage frame count: [0-1.0 KB]: 18772 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]: 18769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18772 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]: 18769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18772 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 29.2 KB
@@ -314,4 +311,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1696847886710,"processId":17074,"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":1697030676623,"processId":26030,"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": 0.6000164747238159,
-            "min": 0.6000164747238159,
-            "max": 1.4511500597000122,
+            "value": 0.19224198162555695,
+            "min": 0.19224198162555695,
+            "max": 1.570914626121521,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18067.6953125,
-            "min": 18067.6953125,
-            "max": 44022.08984375,
+            "value": 5813.3974609375,
+            "min": 5813.3974609375,
+            "max": 47655.265625,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989993.0,
+            "value": 989958.0,
             "min": 29952.0,
-            "max": 989993.0,
+            "max": 989958.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989993.0,
+            "value": 989958.0,
             "min": 29952.0,
-            "max": 989993.0,
+            "max": 989958.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.2799968421459198,
-            "min": -0.10074495524168015,
-            "max": 0.34702029824256897,
+            "value": 0.7307552695274353,
+            "min": -0.05546841025352478,
+            "max": 0.7307552695274353,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 72.79917907714844,
-            "min": -24.27953338623047,
-            "max": 90.22528076171875,
+            "value": 216.30355834960938,
+            "min": -13.367886543273926,
+            "max": 216.30355834960938,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.022046752274036407,
-            "min": -0.1060735285282135,
-            "max": 0.2593739330768585,
+            "value": 0.03569478541612625,
+            "min": 0.03569478541612625,
+            "max": 0.9827675223350525,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 5.732155799865723,
-            "min": -27.8973388671875,
-            "max": 65.10285949707031,
+            "value": 10.565656661987305,
+            "min": 10.565656661987305,
+            "max": 232.91590881347656,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.0709712532466243,
-            "min": 0.06577354117221798,
-            "max": 0.0733196890779211,
+            "value": 0.06640867602770228,
+            "min": 0.06514035453114451,
+            "max": 0.07432111201342195,
             "count": 33
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9935975454527401,
-            "min": 0.4719319477135077,
-            "max": 1.0264756470908953,
+            "value": 0.9961301404155343,
+            "min": 0.48186746976490874,
+            "max": 1.0994104182281457,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.012620828547501932,
-            "min": 0.00013309740357806378,
-            "max": 0.019068041858226224,
+            "value": 0.00941091305469741,
+            "min": 0.0003484809830390088,
+            "max": 0.042529660542911386,
             "count": 33
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.17669159966502704,
-            "min": 0.0017302662465148292,
-            "max": 0.27153414716303814,
+            "value": 0.14116369582046115,
+            "min": 0.0027878478643120702,
+            "max": 0.2977076238003797,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.4963260726857175e-06,
-            "min": 7.4963260726857175e-06,
+            "value": 7.4923975025666634e-06,
+            "min": 7.4923975025666634e-06,
             "max": 0.00029515063018788575,
             "count": 33
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010494856501760005,
-            "min": 0.00010494856501760005,
-            "max": 0.0035072285309238997,
+            "value": 0.00011238596253849996,
+            "min": 0.00011238596253849996,
+            "max": 0.0036341581886139987,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10249874285714286,
-            "min": 0.10249874285714286,
-            "max": 0.19838354285714285,
+            "value": 0.10000000000000002,
+            "min": 0.09999999999999998,
+            "max": 0.10000000000000002,
             "count": 33
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4349824,
-            "min": 1.3886848,
-            "max": 2.5690761,
+            "value": 1.5000000000000002,
+            "min": 0.6999999999999998,
+            "max": 1.5000000000000002,
             "count": 33
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00025962441142857157,
-            "min": 0.00025962441142857157,
-            "max": 0.00983851593142857,
+            "value": 3.4724589999999995e-05,
+            "min": 3.4724589999999995e-05,
+            "max": 0.0009839970742857144,
             "count": 33
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036347417600000017,
-            "min": 0.0036347417600000017,
-            "max": 0.11693070239000002,
+            "value": 0.0005208688499999999,
+            "min": 0.0005208688499999999,
+            "max": 0.0121327214,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00858437828719616,
-            "min": 0.008534661494195461,
-            "max": 0.36013171076774597,
+            "value": 0.04988045617938042,
+            "min": 0.04988045617938042,
+            "max": 0.9820275902748108,
             "count": 33
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12018129974603653,
-            "min": 0.12018129974603653,
-            "max": 2.5209219455718994,
+            "value": 0.7482068538665771,
+            "min": 0.7323045134544373,
+            "max": 6.87419319152832,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 538.1818181818181,
-            "min": 511.8688524590164,
+            "value": 255.9145299145299,
+            "min": 255.9145299145299,
             "max": 999.0,
             "count": 33
         },
         "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 29600.0,
+            "value": 29942.0,
             "min": 15984.0,
-            "max": 33148.0,
+            "max": 32018.0,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.0995147854641631,
+            "value": 1.726989729791625,
             "min": -1.0000000521540642,
-            "max": 1.2594499776938133,
+            "max": 1.726989729791625,
             "count": 33
         },
         "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 59.37379841506481,
-            "min": -30.995201587677002,
-            "max": 70.52919875085354,
+            "value": 202.05779838562012,
+            "min": -32.000001668930054,
+            "max": 202.05779838562012,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.0995147854641631,
+            "value": 1.726989729791625,
             "min": -1.0000000521540642,
-            "max": 1.2594499776938133,
+            "max": 1.726989729791625,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 59.37379841506481,
-            "min": -30.995201587677002,
-            "max": 70.52919875085354,
+            "value": 202.05779838562012,
+            "min": -32.000001668930054,
+            "max": 202.05779838562012,
             "count": 33
         },
         "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04713166055174683,
-            "min": 0.04691060565736344,
-            "max": 7.03644922375679,
+            "value": 0.1326896303251752,
+            "min": 0.1326896303251752,
+            "max": 40.02039594389498,
             "count": 33
         },
         "Pyramids.Policy.RndReward.sum": {
-            "value": 2.5451096697943285,
-            "min": 2.5451096697943285,
-            "max": 112.58318758010864,
+            "value": 15.524686748045497,
+            "min": 15.524686748045497,
+            "max": 640.3263351023197,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1696845628",
+        "start_time_seconds": "1697028329",
         "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
-        "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",
-        "mlagents_version": "0.31.0.dev0",
-        "mlagents_envs_version": "0.31.0.dev0",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training6 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.0.1+cu118",
-        "numpy_version": "1.21.2",
-        "end_time_seconds": "1696847886"
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1697030676"
     },
-    "total": 2258.004996282,
+    "total": 2346.7568116869998,
     "count": 1,
-    "self": 0.8590790250000282,
+    "self": 1.0405180459993062,
     "children": {
         "run_training.setup": {
-            "total": 0.07205637500010198,
+            "total": 0.043942708999566094,
             "count": 1,
-            "self": 0.07205637500010198
+            "self": 0.043942708999566094
         },
         "TrainerController.start_learning": {
-            "total": 2257.0738608819997,
+            "total": 2345.672350932001,
             "count": 1,
-            "self": 1.378231863081055,
+            "self": 1.3403733387622196,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.2381678679998913,
+                    "total": 3.42468070599989,
                     "count": 1,
-                    "self": 3.2381678679998913
+                    "self": 3.42468070599989
                 },
                 "TrainerController.advance": {
-                    "total": 2252.331038375919,
-                    "count": 63425,
-                    "self": 1.4844337339409321,
+                    "total": 2340.7143047812388,
+                    "count": 64446,
+                    "self": 1.344616622475769,
                     "children": {
                         "env_step": {
-                            "total": 1551.1611032820083,
-                            "count": 63425,
-                            "self": 1422.1959614800649,
+                            "total": 1702.8825311429227,
+                            "count": 64446,
+                            "self": 1577.4343140297942,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 128.12189231891625,
-                                    "count": 63425,
-                                    "self": 4.7368422880535945,
+                                    "total": 124.64412061116309,
+                                    "count": 64446,
+                                    "self": 4.402678408201609,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 123.38505003086266,
-                                            "count": 62561,
-                                            "self": 123.38505003086266
+                                            "total": 120.24144220296148,
+                                            "count": 62572,
+                                            "self": 120.24144220296148
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8432494830271935,
-                                    "count": 63425,
+                                    "total": 0.8040965019654323,
+                                    "count": 64446,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2252.3510538129563,
-                                            "count": 63425,
+                                            "total": 2340.758332195177,
+                                            "count": 64446,
                                             "is_parallel": true,
-                                            "self": 950.3590294159553,
+                                            "self": 877.6269186870013,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020596209997165715,
+                                                            "total": 0.001989801000490843,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006466840000030061,
+                                                            "self": 0.0006273700018937234,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0014129369997135655,
+                                                                    "total": 0.0013624309985971195,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0014129369997135655
+                                                                    "self": 0.0013624309985971195
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0694124430001466,
+                                                            "total": 0.07798009999987698,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006045020004421531,
+                                                            "self": 0.000597982999352098,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004962269999850832,
+                                                                    "total": 0.0005286890000206768,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004962269999850832
+                                                                    "self": 0.0005286890000206768
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.06628340799989019,
+                                                                    "total": 0.07509337800001958,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.06628340799989019
+                                                                    "self": 0.07509337800001958
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002028305999829172,
+                                                                    "total": 0.0017600500004846253,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042453399964870187,
+                                                                    "self": 0.00037057199915579986,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.00160377200018047,
+                                                                            "total": 0.0013894780013288255,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.00160377200018047
+                                                                            "self": 0.0013894780013288255
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1301.992024397001,
-                                                    "count": 63424,
+                                                    "total": 1463.1314135081757,
+                                                    "count": 64445,
                                                     "is_parallel": true,
-                                                    "self": 34.676325190183434,
+                                                    "self": 33.57405870530329,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.97995316386914,
-                                                            "count": 63424,
+                                                            "total": 22.955753032837492,
+                                                            "count": 64445,
                                                             "is_parallel": true,
-                                                            "self": 25.97995316386914
+                                                            "self": 22.955753032837492
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1129.322513895043,
-                                                            "count": 63424,
+                                                            "total": 1311.566378843152,
+                                                            "count": 64445,
                                                             "is_parallel": true,
-                                                            "self": 1129.322513895043
+                                                            "self": 1311.566378843152
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 112.01323214790546,
-                                                            "count": 63424,
+                                                            "total": 95.03522292688285,
+                                                            "count": 64445,
                                                             "is_parallel": true,
-                                                            "self": 22.079889371990703,
+                                                            "self": 18.735387731310766,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 89.93334277591475,
-                                                                    "count": 507392,
+                                                                    "total": 76.29983519557209,
+                                                                    "count": 515560,
                                                                     "is_parallel": true,
-                                                                    "self": 89.93334277591475
+                                                                    "self": 76.29983519557209
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 699.6855013599697,
-                            "count": 63425,
-                            "self": 2.6304920551001487,
+                            "total": 636.4871570158402,
+                            "count": 64446,
+                            "self": 2.536269047989663,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 124.83358912288122,
-                                    "count": 63425,
-                                    "self": 124.60570166388106,
+                                    "total": 121.15106498483419,
+                                    "count": 64446,
+                                    "self": 120.47755503783446,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.22788745900015783,
-                                            "count": 2,
-                                            "self": 0.22788745900015783
+                                            "total": 0.6735099469997294,
+                                            "count": 5,
+                                            "self": 0.6735099469997294
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 572.2214201819884,
-                                    "count": 454,
-                                    "self": 364.5622983060184,
+                                    "total": 512.7998229830164,
+                                    "count": 448,
+                                    "self": 300.0865035119996,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 207.65912187596996,
-                                            "count": 22773,
-                                            "self": 207.65912187596996
+                                            "total": 212.7133194710168,
+                                            "count": 22815,
+                                            "self": 212.7133194710168
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3760000001639128e-06,
+                    "total": 1.5260011423379183e-06,
                     "count": 1,
-                    "self": 1.3760000001639128e-06
+                    "self": 1.5260011423379183e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12642139899980975,
+                    "total": 0.19299057999887737,
                     "count": 1,
-                    "self": 0.002069836999908148,
+                    "self": 0.005388030000176514,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.1243515619999016,
+                            "total": 0.18760254999870085,
                             "count": 1,
-                            "self": 0.1243515619999016
+                            "self": 0.18760254999870085
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,46 +2,64 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499997,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499997.onnx",
-                "reward": 1.3089999705553055,
-                "creation_time": 1696846694.346217,
+                "steps": 399945,
+                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-399945.onnx",
+                "reward": 0.984749985858798,
+                "creation_time": 1697029155.0306525,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499997.pt"
+                    "results/Pyramids Training6/Pyramids/Pyramids-399945.pt"
                 ]
             },
             {
-                "steps": 999901,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999901.onnx",
+                "steps": 599946,
+                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-599946.onnx",
+                "reward": 1.7097499668598175,
+                "creation_time": 1697029661.467683,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training6/Pyramids/Pyramids-599946.pt"
+                ]
+            },
+            {
+                "steps": 799906,
+                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-799906.onnx",
                 "reward": null,
-                "creation_time": 1696847885.7750146,
+                "creation_time": 1697030162.5838199,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999901.pt"
+                    "results/Pyramids Training6/Pyramids/Pyramids-799906.pt"
+                ]
+            },
+            {
+                "steps": 999901,
+                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-999901.onnx",
+                "reward": 1.704285700406347,
+                "creation_time": 1697030675.4404697,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training6/Pyramids/Pyramids-999901.pt"
                 ]
             },
             {
                 "steps": 1000029,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000029.onnx",
-                "reward": null,
-                "creation_time": 1696847885.9189181,
+                "file_path": "results/Pyramids Training6/Pyramids/Pyramids-1000029.onnx",
+                "reward": 1.704285700406347,
+                "creation_time": 1697030675.6403673,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000029.pt"
+                    "results/Pyramids Training6/Pyramids/Pyramids-1000029.pt"
                 ]
             }
         ],
         "final_checkpoint": {
             "steps": 1000029,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1696847885.9189181,
+            "file_path": "results/Pyramids Training6/Pyramids.onnx",
+            "reward": 1.704285700406347,
+            "creation_time": 1697030675.6403673,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000029.pt"
+                "results/Pyramids Training6/Pyramids/Pyramids-1000029.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "0.31.0.dev0",
+        "mlagents_version": "1.1.0.dev0",
         "torch_version": "2.0.1+cu118"
     }
 }