3M Step Trainning Agent

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cb3011db573186260a36df0c6a2186bef88152b82fa6d3296869a63bc143e1
+oid sha256:700dbdd475a0a465cfd70021c354ce520d0ff20f55f8b3d1d99752ee9a2138cc
 size 1418184

Pyramids/{Pyramids-1000017.onnx → Pyramids-1499952.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75cb3011db573186260a36df0c6a2186bef88152b82fa6d3296869a63bc143e1
+oid sha256:f2d15d7eff3b1ccd8e3407002b03a65ecc076480e829deeee458c4fd9f3340fe
 size 1418184

Pyramids/{Pyramids-1000017.pt → Pyramids-1499952.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117db6982def4abb9c9d6df85cb3f68c72655553bd7f9d40d8a53026d2ab03c3
+oid sha256:f767634c47773f4827ff42516eac88cd19df617e824cfb26a04dcba10127baa2
 size 8650990

Pyramids/Pyramids-1999894.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e178573fc40fed19c8869769cf13e810daaa7d99ff0aeb36b57d8b741b1c83
+size 1418184

Pyramids/Pyramids-1999894.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78cbdaa073549fbed82852c8e28d55ef2dddec272428270e12e761c5fe75fcc
+size 8650990

Pyramids/Pyramids-2499504.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ea71a47eedc6a5211b9c9761fc1729b5c6521a60dada5909d8e5c5423b6b3d
+size 1418184

Pyramids/Pyramids-2499504.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18d274e5f560ed8525258582c164958ce937b1b5a86c40bacd6e5dc7dde071e8
+size 8650990

Pyramids/Pyramids-2999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700dbdd475a0a465cfd70021c354ce520d0ff20f55f8b3d1d99752ee9a2138cc
+size 1418184

Pyramids/Pyramids-2999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9871eec178a5532b6e0535095b625dc260d9ebf7f913df8b2a5d2e3bdd7b2c92
+size 8650990

Pyramids/Pyramids-3000240.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700dbdd475a0a465cfd70021c354ce520d0ff20f55f8b3d1d99752ee9a2138cc
+size 1418184

Pyramids/Pyramids-3000240.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa901b5b7509f1eb47ea402ed1da44a49355331f66b529fd3fa0c998f72ac6a
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117db6982def4abb9c9d6df85cb3f68c72655553bd7f9d40d8a53026d2ab03c3
+oid sha256:4fa901b5b7509f1eb47ea402ed1da44a49355331f66b529fd3fa0c998f72ac6a
 size 8650990

Pyramids/events.out.tfevents.1682361544.f2233c7926ec.13248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b3df4c2b7a485e2d790ce34255ffe9539141c94e6ab44b60ea4f7ade1ffba03
+size 1423

Pyramids/events.out.tfevents.1682361680.f2233c7926ec.13898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9893f660b875692dcdc7b7bc7450cc711fb17055d403409d48a21e0dbf7911e9
+size 620812

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": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 512, "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": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -51,8 +51,8 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
-    time_horizon: 128
+    max_steps: 3000000
+    time_horizon: 512
     summary_freq: 30000
     threaded: false
     self_play: null
@@ -77,10 +77,10 @@ engine_settings:
   no_graphics: true
 environment_parameters: null
 checkpoint_settings:
-  run_id: Pyramids Training
+  run_id: Pyramids_Training
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: 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] 55114 [Flags] 2 [Guid] 2253166765 [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] 55466 [Flags] 2 [Guid] 670253028 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
-PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
-Unable to load player prefs
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
 [Subsystems] Discovering subsystems at path /content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.094 seconds
+- Completed reload, in  0.087 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: 0.968731 ms
+UnloadTime: 0.797879 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]: 7048 frames, [32.0 KB-64.0 KB]: 9440 frames, [64.0 KB-128.0 KB]: 2276 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 1413 frames, [32.0 KB-64.0 KB]: 24138 frames, [64.0 KB-128.0 KB]: 11987 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
@@ -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]: 18466 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 44 frames, [1.0 MB-2.0 MB]: 37495 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 12983
+  Peak main deferred allocation count 12986
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 260 frames, [16.0 MB-32.0 MB]: 18505 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 37538 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 29.3 MB
+      Peak Block count 2
+      Peak Allocated memory 23.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37539 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.4 MB
+      Peak Allocated memory 23.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37538 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]: 18765 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 37539 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 67 frames, [1.0 MB-2.0 MB]: 37472 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]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 37538 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 4.7 MB
@@ -291,21 +288,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18765 frames
+      Peak usage frame count: [0-1.0 KB]: 37539 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]: 18765 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 37539 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]: 18765 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 37539 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":1682361063258,"processId":1409,"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":1682366838223,"processId":13914,"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

@@ -2,249 +2,249 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.46900054812431335,
-            "min": 0.4589627981185913,
-            "max": 1.3092679977416992,
-            "count": 33
+            "value": 0.19219397008419037,
+            "min": 0.18550704419612885,
+            "max": 0.49777692556381226,
+            "count": 67
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 14130.048828125,
-            "min": 13710.13671875,
-            "max": 39717.953125,
-            "count": 33
+            "value": 5624.3642578125,
+            "min": 5342.916015625,
+            "max": 14828.44921875,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 226.48507462686567,
+            "min": 208.86013986013987,
+            "max": 533.1666666666666,
+            "count": 67
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30349.0,
+            "min": 17114.0,
+            "max": 31990.0,
+            "count": 67
         },
         "Pyramids.Step.mean": {
-            "value": 989968.0,
-            "min": 29921.0,
-            "max": 989968.0,
-            "count": 33
+            "value": 2999938.0,
+            "min": 1019997.0,
+            "max": 2999938.0,
+            "count": 67
         },
         "Pyramids.Step.sum": {
-            "value": 989968.0,
-            "min": 29921.0,
-            "max": 989968.0,
-            "count": 33
+            "value": 2999938.0,
+            "min": 1019997.0,
+            "max": 2999938.0,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3445166349411011,
-            "min": -0.09646021574735641,
-            "max": 0.3445166349411011,
-            "count": 33
+            "value": 0.6666208505630493,
+            "min": 0.36387720704078674,
+            "max": 0.7674804925918579,
+            "count": 67
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 89.57432556152344,
-            "min": -23.15045166015625,
-            "max": 89.57432556152344,
-            "count": 33
+            "value": 93.32691955566406,
+            "min": 21.42395782470703,
+            "max": 109.74971008300781,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.05449855327606201,
-            "min": -0.009074815548956394,
-            "max": 0.6867399215698242,
-            "count": 33
+            "value": -0.0011070820037275553,
+            "min": -0.0011070820037275553,
+            "max": 0.06387358158826828,
+            "count": 67
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 14.169623374938965,
-            "min": -2.323152780532837,
-            "max": 162.75735473632812,
-            "count": 33
+            "value": -0.15499147772789001,
+            "min": -0.15499147772789001,
+            "max": 6.659514904022217,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.774075158108446,
+            "min": 1.0004732936620713,
+            "max": 1.7912237502478219,
+            "count": 67
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 235.9519960284233,
+            "min": 59.13059860467911,
+            "max": 256.14499628543854,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.774075158108446,
+            "min": 1.0004732936620713,
+            "max": 1.7912237502478219,
+            "count": 67
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 235.9519960284233,
+            "min": 59.13059860467911,
+            "max": 256.14499628543854,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.013118862431298126,
+            "min": 0.01211571304853745,
+            "max": 0.05650609043659642,
+            "count": 67
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.7448087033626507,
+            "min": 1.703937309619505,
+            "max": 3.3903654261957854,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06895477416645833,
-            "min": 0.06470380895277394,
-            "max": 0.07430250059412977,
-            "count": 33
+            "value": 0.07021938906689147,
+            "min": 0.06433822517548483,
+            "max": 0.07532237745243354,
+            "count": 67
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9653668383304166,
-            "min": 0.5201175041589083,
-            "max": 1.0845711148223,
-            "count": 33
+            "value": 0.9830714469364806,
+            "min": 0.5112304518232115,
+            "max": 1.038050119580662,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.015018212987159423,
-            "min": 0.0006393421300093562,
-            "max": 0.05055531119645662,
-            "count": 33
+            "value": 0.01699921610653327,
+            "min": 0.012220533279286051,
+            "max": 0.019389853853861164,
+            "count": 67
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21025498182023192,
-            "min": 0.008950789820130988,
-            "max": 0.35388717837519634,
-            "count": 33
+            "value": 0.23798902549146578,
+            "min": 0.08875731165296516,
+            "max": 0.2533198153621148,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.764333126207147e-06,
-            "min": 7.764333126207147e-06,
-            "max": 0.00029515063018788575,
-            "count": 33
+            "value": 1.5522851968904773e-06,
+            "min": 1.5522851968904773e-06,
+            "max": 0.00019890410512721427,
+            "count": 67
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010870066376690005,
-            "min": 0.00010870066376690005,
-            "max": 0.0035071496309501994,
-            "count": 33
+            "value": 2.1731992756466683e-05,
+            "min": 2.1731992756466683e-05,
+            "max": 0.0027090938969688665,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10258807857142857,
-            "min": 0.10258807857142857,
-            "max": 0.19838354285714285,
-            "count": 33
+            "value": 0.10051739523809525,
+            "min": 0.10051739523809525,
+            "max": 0.16630135714285715,
+            "count": 67
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4362331,
-            "min": 1.3886848,
-            "max": 2.5690498000000006,
-            "count": 33
+            "value": 1.4072435333333335,
+            "min": 1.1641095000000001,
+            "max": 2.3030311333333335,
+            "count": 67
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002685490492857143,
-            "min": 0.0002685490492857143,
-            "max": 0.00983851593142857,
-            "count": 33
+            "value": 6.168778428571434e-05,
+            "min": 6.168778428571434e-05,
+            "max": 0.006633505578571429,
+            "count": 67
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.0037596866900000006,
-            "min": 0.0037596866900000006,
-            "max": 0.11692807502,
-            "count": 33
+            "value": 0.0008636289800000007,
+            "min": 0.0008636289800000007,
+            "max": 0.09035281022,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.01126160193234682,
-            "min": 0.01126160193234682,
-            "max": 0.7172831296920776,
-            "count": 33
+            "value": 0.005565266590565443,
+            "min": 0.005470035132020712,
+            "max": 0.011300760321319103,
+            "count": 67
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.15766242146492004,
-            "min": 0.15766242146492004,
-            "max": 5.020981788635254,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 464.5652173913044,
-            "min": 464.5652173913044,
-            "max": 999.0,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 32055.0,
-            "min": 16848.0,
-            "max": 34094.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.3015264464432703,
-            "min": -0.9999871489501768,
-            "max": 1.3015264464432703,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 88.50379835814238,
-            "min": -30.999601617455482,
-            "max": 88.50379835814238,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.3015264464432703,
-            "min": -0.9999871489501768,
-            "max": 1.3015264464432703,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 88.50379835814238,
-            "min": -30.999601617455482,
-            "max": 88.50379835814238,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.05463703287066036,
-            "min": 0.05463703287066036,
-            "max": 15.668482102891979,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.7153182352049043,
-            "min": 3.7153182352049043,
-            "max": 266.3641957491636,
-            "count": 33
+            "value": 0.07791373133659363,
+            "min": 0.07111045718193054,
+            "max": 0.13362309336662292,
+            "count": 67
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 67
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1682358817",
+        "start_time_seconds": "1682361679",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids_Training --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
         "mlagents_envs_version": "0.31.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1682361063"
+        "end_time_seconds": "1682366838"
     },
-    "total": 2245.483663553,
+    "total": 5158.253907008,
     "count": 1,
-    "self": 0.8911281190003137,
+    "self": 0.5404954800005726,
     "children": {
         "run_training.setup": {
-            "total": 0.11185266600000432,
+            "total": 0.10461595600008877,
             "count": 1,
-            "self": 0.11185266600000432
+            "self": 0.10461595600008877
         },
         "TrainerController.start_learning": {
-            "total": 2244.480682768,
+            "total": 5157.6087955719995,
             "count": 1,
-            "self": 1.5369179769959374,
+            "self": 3.286220517969923,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.16873750000002,
+                    "total": 3.6928145850001783,
                     "count": 1,
-                    "self": 4.16873750000002
+                    "self": 3.6928145850001783
                 },
                 "TrainerController.advance": {
-                    "total": 2238.5942833030035,
-                    "count": 63468,
-                    "self": 1.7590164259727317,
+                    "total": 5150.533193084029,
+                    "count": 130712,
+                    "self": 3.4350088819392113,
                     "children": {
                         "env_step": {
-                            "total": 1596.429881029029,
-                            "count": 63468,
-                            "self": 1476.6562448450893,
+                            "total": 3906.725981640026,
+                            "count": 130712,
+                            "self": 3663.215075721788,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 118.77874978494879,
-                                    "count": 63468,
-                                    "self": 5.141452788914592,
+                                    "total": 241.43405281694277,
+                                    "count": 130712,
+                                    "self": 10.486002190841191,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 113.6372969960342,
-                                            "count": 62550,
-                                            "self": 113.6372969960342
+                                            "total": 230.94805062610158,
+                                            "count": 125128,
+                                            "self": 230.94805062610158
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.9948863989909569,
-                                    "count": 63468,
+                                    "total": 2.0768531012954554,
+                                    "count": 130712,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2238.565739711998,
-                                            "count": 63468,
+                                            "total": 5145.163647358251,
+                                            "count": 130712,
                                             "is_parallel": true,
-                                            "self": 885.75003951398,
+                                            "self": 1741.3275867404564,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004885444000024108,
+                                                            "total": 0.001905523000004905,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0035739690001150848,
+                                                            "self": 0.0006361430005199509,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013114749999090236,
+                                                                    "total": 0.0012693799994849542,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013114749999090236
+                                                                    "self": 0.0012693799994849542
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.049109283000007053,
+                                                            "total": 0.04917733299998872,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005969039999627057,
+                                                            "self": 0.0005287529993438511,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005557709999948202,
+                                                                    "total": 0.0004954010000801645,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005557709999948202
+                                                                    "self": 0.0004954010000801645
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0461562800000479,
+                                                                    "total": 0.04648904800023956,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0461562800000479
+                                                                    "self": 0.04648904800023956
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018003280000016275,
+                                                                    "total": 0.001664131000325142,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00042112499994573227,
+                                                                    "self": 0.0003975099998569931,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013792030000558952,
+                                                                            "total": 0.0012666210004681488,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013792030000558952
+                                                                            "self": 0.0012666210004681488
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1352.815700198018,
-                                                    "count": 63467,
+                                                    "total": 3403.836060617795,
+                                                    "count": 130711,
                                                     "is_parallel": true,
-                                                    "self": 34.659434997051676,
+                                                    "self": 67.67384928773436,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 25.352889859031052,
-                                                            "count": 63467,
+                                                            "total": 50.31187488609794,
+                                                            "count": 130711,
                                                             "is_parallel": true,
-                                                            "self": 25.352889859031052
+                                                            "self": 50.31187488609794
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1190.1519725339604,
-                                                            "count": 63467,
+                                                            "total": 3076.8317580709095,
+                                                            "count": 130711,
                                                             "is_parallel": true,
-                                                            "self": 1190.1519725339604
+                                                            "self": 3076.8317580709095
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 102.65140280797482,
-                                                            "count": 63467,
+                                                            "total": 209.01857837305306,
+                                                            "count": 130711,
                                                             "is_parallel": true,
-                                                            "self": 22.571380099078738,
+                                                            "self": 47.045237717555665,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 80.08002270889608,
-                                                                    "count": 507736,
+                                                                    "total": 161.9733406554974,
+                                                                    "count": 1045688,
                                                                     "is_parallel": true,
-                                                                    "self": 80.08002270889608
+                                                                    "self": 161.9733406554974
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 640.4053858480016,
-                            "count": 63468,
-                            "self": 2.8908552609842673,
+                            "total": 1240.3722025620646,
+                            "count": 130712,
+                            "self": 7.083264434037119,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 113.12287576202101,
-                                    "count": 63468,
-                                    "self": 112.83784743902123,
+                                    "total": 196.06929223203406,
+                                    "count": 130712,
+                                    "self": 195.45935048403317,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.28502832299977854,
-                                            "count": 2,
-                                            "self": 0.28502832299977854
+                                            "total": 0.6099417480008924,
+                                            "count": 4,
+                                            "self": 0.6099417480008924
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 524.3916548249963,
-                                    "count": 453,
-                                    "self": 335.63997934299266,
+                                    "total": 1037.2196458959934,
+                                    "count": 901,
+                                    "self": 661.1039385619292,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 188.75167548200363,
-                                            "count": 22764,
-                                            "self": 188.75167548200363
+                                            "total": 376.11570733406415,
+                                            "count": 45618,
+                                            "self": 376.11570733406415
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.4750003174412996e-06,
+                    "total": 1.1880001693498343e-06,
                     "count": 1,
-                    "self": 1.4750003174412996e-06
+                    "self": 1.1880001693498343e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18074251300004107,
+                    "total": 0.09656619700035662,
                     "count": 1,
-                    "self": 0.0021036930002082954,
+                    "self": 0.0018388770004094113,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.17863881999983278,
+                            "total": 0.09472731999994721,
                             "count": 1,
-                            "self": 0.17863881999983278
+                            "self": 0.09472731999994721
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499962,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499962.onnx",
-                "reward": -0.23600004613399506,
-                "creation_time": 1682359912.763916,
+                "steps": 1499952,
+                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-1499952.onnx",
+                "reward": 1.7874285323279244,
+                "creation_time": 1682362915.6562793,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499962.pt"
+                    "results/Pyramids_Training/Pyramids/Pyramids-1499952.pt"
                 ]
             },
             {
-                "steps": 999913,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999913.onnx",
-                "reward": 1.4964000016450882,
-                "creation_time": 1682361062.2182255,
+                "steps": 1999894,
+                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-1999894.onnx",
+                "reward": 1.7401428478104728,
+                "creation_time": 1682364208.1013923,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999913.pt"
+                    "results/Pyramids_Training/Pyramids/Pyramids-1999894.pt"
                 ]
             },
             {
-                "steps": 1000017,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000017.onnx",
-                "reward": 1.0803666586677234,
-                "creation_time": 1682361062.414394,
+                "steps": 2499504,
+                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-2499504.onnx",
+                "reward": 1.4739999175071716,
+                "creation_time": 1682365509.5769775,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000017.pt"
+                    "results/Pyramids_Training/Pyramids/Pyramids-2499504.pt"
+                ]
+            },
+            {
+                "steps": 2999938,
+                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-2999938.onnx",
+                "reward": 1.628399956226349,
+                "creation_time": 1682366837.5881143,
+                "auxillary_file_paths": [
+                    "results/Pyramids_Training/Pyramids/Pyramids-2999938.pt"
+                ]
+            },
+            {
+                "steps": 3000240,
+                "file_path": "results/Pyramids_Training/Pyramids/Pyramids-3000240.onnx",
+                "reward": 1.6401666104793549,
+                "creation_time": 1682366837.70389,
+                "auxillary_file_paths": [
+                    "results/Pyramids_Training/Pyramids/Pyramids-3000240.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000017,
-            "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.0803666586677234,
-            "creation_time": 1682361062.414394,
+            "steps": 3000240,
+            "file_path": "results/Pyramids_Training/Pyramids.onnx",
+            "reward": 1.6401666104793549,
+            "creation_time": 1682366837.70389,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000017.pt"
+                "results/Pyramids_Training/Pyramids/Pyramids-3000240.pt"
             ]
         }
     },