First training of PPO agent on Pyramids environment.

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f6b5593ad7fb701e9e8d73427cce4d9071aabf2e3fd844bf6998a6e247c875
+oid sha256:76fb6ae696d9c928e6cd05bedca981176d36eb7e2cdaa791ea8d08bf4b26f2c4
 size 1417437

Pyramids/Pyramids-1000079.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fb6ae696d9c928e6cd05bedca981176d36eb7e2cdaa791ea8d08bf4b26f2c4
+size 1417437

Pyramids/Pyramids-1000079.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a40c63024c840e53f0d6c12d33ebe854c377f23eb592ac6dfc4c263ae474ecf8
+size 8651427

Pyramids/Pyramids-999951.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76fb6ae696d9c928e6cd05bedca981176d36eb7e2cdaa791ea8d08bf4b26f2c4
+size 1417437

Pyramids/Pyramids-999951.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f0b9855a5106f92087d00567b2f9e8548203117dcf880aef90f10f960a5db84
+size 8651427

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdbb1beaacef82ccc7328edb200fd1ee6d2ea064c014d896c9d29280dbd3321
+oid sha256:a40c63024c840e53f0d6c12d33ebe854c377f23eb592ac6dfc4c263ae474ecf8
 size 8651427

Pyramids/events.out.tfevents.1673946854.2694b56eafa7.33402.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58be618d8e6fb728d4d1de68f5fad87c37b7093d33175ee341e21479cddb0799
+size 55097

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "checkpoint_interval": 500000, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -78,7 +78,7 @@ checkpoint_settings:
   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) 172.28.0.2
-Multi-casting "[IP] 172.28.0.2 [Port] 55227 [Flags] 2 [Guid] 4117401756 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 172.28.0.2 [Port] 55272 [Flags] 2 [Guid] 3621104877 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.2) [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
@@ -15,6 +12,7 @@ NullGfxDevice:
     Version:  NULL 1.0 [1.0]
     Renderer: Null Device
     Vendor:   Unity Technologies
+xcb_connection_has_error() returned true
 ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
 ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
 ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
@@ -24,6 +22,7 @@ ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_refer returned err
 ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
 ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+xcb_connection_has_error() returned true
 Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
 ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
 ALSA lib conf.c:4528:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
@@ -36,7 +35,7 @@ ALSA lib pcm.c:2495:(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  0.127 seconds
+- Completed reload, in  0.135 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)
@@ -68,9 +67,250 @@ 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: 1.312864 ms
+UnloadTime: 1.267287 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.
-PlayerConnection::CleanupXIO:  fatal IO error 11 (Resource temporarily unavailable) on X server ":0"
-      after 234 requests (234 known processed) with 0 events remaining.
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 348 frames, [32.0 KB-64.0 KB]: 2567 frames, [64.0 KB-128.0 KB]: 1212 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
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      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 10]
+      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 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD mixer thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      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 11]
+      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 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      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 13]
+      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 0]
+      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 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [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 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 37 frames, [1.0 MB-2.0 MB]: 4091 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.1 MB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 11822
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 4127 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 25.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 4128 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 21.7 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 4127 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]: 4128 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 57 frames, [1.0 MB-2.0 MB]: 4071 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]: 4127 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
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.2 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 4128 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]: 4128 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]: 4128 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 27.4 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1673947632117,"processId":33434,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"Thread":34460},{"Manager":10603},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3447},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,256 +2,256 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.4624595046043396,
-            "min": 0.4624595046043396,
-            "max": 1.3868093490600586,
-            "count": 26
+            "value": 0.3690907955169678,
+            "min": 0.3690907955169678,
+            "max": 0.46054497361183167,
+            "count": 7
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 13947.7783203125,
-            "min": 13947.7783203125,
-            "max": 42070.25,
-            "count": 26
+            "value": 11078.62890625,
+            "min": 11078.62890625,
+            "max": 13823.7177734375,
+            "count": 7
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 301.4742268041237,
+            "min": 278.1636363636364,
+            "max": 332.9625,
+            "count": 7
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29243.0,
+            "min": 26637.0,
+            "max": 30793.0,
+            "count": 7
         },
         "Pyramids.Step.mean": {
-            "value": 779972.0,
-            "min": 29952.0,
-            "max": 779972.0,
-            "count": 26
+            "value": 989899.0,
+            "min": 809943.0,
+            "max": 989899.0,
+            "count": 7
         },
         "Pyramids.Step.sum": {
-            "value": 779972.0,
-            "min": 29952.0,
-            "max": 779972.0,
-            "count": 26
+            "value": 989899.0,
+            "min": 809943.0,
+            "max": 989899.0,
+            "count": 7
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.568676233291626,
-            "min": -0.14658166468143463,
-            "max": 0.568676233291626,
-            "count": 26
+            "value": 0.6117339730262756,
+            "min": 0.5805515646934509,
+            "max": 0.652145504951477,
+            "count": 7
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 155.81729125976562,
-            "min": -34.73985290527344,
-            "max": 155.81729125976562,
-            "count": 26
+            "value": 175.56764221191406,
+            "min": 156.11248779296875,
+            "max": 185.86146545410156,
+            "count": 7
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.015208727680146694,
-            "min": 0.0010243135038763285,
-            "max": 0.271362841129303,
-            "count": 26
+            "value": 0.005026842933148146,
+            "min": -0.017886633053421974,
+            "max": 0.005214397795498371,
+            "count": 7
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 4.167191505432129,
-            "min": 0.27144306898117065,
-            "max": 65.39844512939453,
-            "count": 26
+            "value": 1.4427039623260498,
+            "min": -5.097690582275391,
+            "max": 1.4427039623260498,
+            "count": 7
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6561877459895855,
+            "min": 1.6482744545061538,
+            "max": 1.723315299631239,
+            "count": 7
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 162.30639910697937,
+            "min": 133.3629986345768,
+            "max": 191.28799825906754,
+            "count": 7
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6561877459895855,
+            "min": 1.6482744545061538,
+            "max": 1.723315299631239,
+            "count": 7
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 162.30639910697937,
+            "min": 133.3629986345768,
+            "max": 191.28799825906754,
+            "count": 7
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03455416573602373,
+            "min": 0.03330021994193672,
+            "max": 0.041914856773655626,
+            "count": 7
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.386308242130326,
+            "min": 3.3531885418924503,
+            "max": 3.8358080207544845,
+            "count": 7
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06873180995139086,
-            "min": 0.06573921082911381,
-            "max": 0.07225488690293141,
-            "count": 26
+            "value": 0.06926667617969977,
+            "min": 0.0656328608889626,
+            "max": 0.07174140105967243,
+            "count": 7
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0309771492708628,
-            "min": 0.4892529376180998,
-            "max": 1.060590602826172,
-            "count": 26
+            "value": 0.9697334665157968,
+            "min": 0.9188600524454764,
+            "max": 1.0351087275679067,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.014059386240680595,
-            "min": 0.0009458740503079729,
-            "max": 0.015242839636768965,
-            "count": 26
+            "value": 0.01623379010372079,
+            "min": 0.014796004913827905,
+            "max": 0.016680958969421532,
+            "count": 7
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.21089079361020893,
-            "min": 0.010317290585335015,
-            "max": 0.2133997549147655,
-            "count": 26
+            "value": 0.22727306145209109,
+            "min": 0.19234806387976278,
+            "max": 0.23698257621920976,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.055377648209996e-05,
-            "min": 7.055377648209996e-05,
-            "max": 0.00029515063018788575,
-            "count": 26
+            "value": 7.77710455052143e-06,
+            "min": 7.77710455052143e-06,
+            "max": 6.129377187646153e-05,
+            "count": 7
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.0010583066472314995,
-            "min": 0.0010583066472314995,
-            "max": 0.0033750247749918,
-            "count": 26
+            "value": 0.00010887946370730003,
+            "min": 0.00010887946370730003,
+            "max": 0.000796819034394,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.12351789999999999,
-            "min": 0.12351789999999999,
-            "max": 0.19838354285714285,
-            "count": 26
+            "value": 0.1025923357142857,
+            "min": 0.1025923357142857,
+            "max": 0.12043123076923078,
+            "count": 7
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.8527684999999998,
-            "min": 1.3886848,
-            "max": 2.4432375,
-            "count": 26
+            "value": 1.4362926999999999,
+            "min": 1.4362926999999999,
+            "max": 1.7173414,
+            "count": 7
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00235943821,
-            "min": 0.00235943821,
-            "max": 0.00983851593142857,
-            "count": 26
+            "value": 0.00026897433785714304,
+            "min": 0.00026897433785714304,
+            "max": 0.002051079953846154,
+            "count": 7
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.03539157315,
-            "min": 0.03539157315,
-            "max": 0.11251831918,
-            "count": 26
+            "value": 0.0037656407300000025,
+            "min": 0.0037656407300000025,
+            "max": 0.026664039400000002,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.011437034234404564,
-            "min": 0.011437034234404564,
-            "max": 0.39684292674064636,
-            "count": 26
+            "value": 0.011005385778844357,
+            "min": 0.011005385778844357,
+            "max": 0.012201069854199886,
+            "count": 7
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.1715555191040039,
-            "min": 0.1683458536863327,
-            "max": 2.777900457382202,
-            "count": 26
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 349.3448275862069,
-            "min": 332.43956043956047,
-            "max": 999.0,
-            "count": 26
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30393.0,
-            "min": 15984.0,
-            "max": 34041.0,
-            "count": 26
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.5613454385575922,
-            "min": -1.0000000521540642,
-            "max": 1.6216955381962987,
-            "count": 26
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 137.39839859306812,
-            "min": -30.676601640880108,
-            "max": 145.9525984376669,
-            "count": 26
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.5613454385575922,
-            "min": -1.0000000521540642,
-            "max": 1.6216955381962987,
-            "count": 26
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 137.39839859306812,
-            "min": -30.676601640880108,
-            "max": 145.9525984376669,
-            "count": 26
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.04159902990431874,
-            "min": 0.04159902990431874,
-            "max": 7.765137803740799,
-            "count": 26
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.660714631580049,
-            "min": 3.660714631580049,
-            "max": 124.24220485985279,
-            "count": 26
+            "value": 0.15407539904117584,
+            "min": 0.15407539904117584,
+            "max": 0.18288809061050415,
+            "count": 7
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 26
+            "count": 7
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 26
+            "count": 7
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673944417",
+        "start_time_seconds": "1673946849",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "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": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673946819"
+        "end_time_seconds": "1673947632"
     },
-    "total": 2401.6863892289994,
+    "total": 782.9304163909992,
     "count": 1,
-    "self": 0.39779570499922556,
+    "self": 1.513138227998752,
     "children": {
         "run_training.setup": {
-            "total": 0.14710872799969366,
+            "total": 0.1443556410004021,
             "count": 1,
-            "self": 0.14710872799969366
+            "self": 0.1443556410004021
         },
         "TrainerController.start_learning": {
-            "total": 2401.1414847960004,
+            "total": 781.272922522,
             "count": 1,
-            "self": 1.5874755200247819,
+            "self": 0.47133834608575853,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.51566898100009,
+                    "total": 5.516701714999726,
                     "count": 1,
-                    "self": 4.51566898100009
+                    "self": 5.516701714999726
                 },
                 "TrainerController.advance": {
-                    "total": 2394.855636035976,
-                    "count": 49824,
-                    "self": 1.853121960093631,
+                    "total": 775.1072918309155,
+                    "count": 14322,
+                    "self": 0.5090716710265042,
                     "children": {
                         "env_step": {
-                            "total": 1494.0950928778411,
-                            "count": 49824,
-                            "self": 1391.7245817680168,
+                            "total": 521.0917065080475,
+                            "count": 14322,
+                            "self": 492.06629796500874,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 101.23936362989662,
-                                    "count": 49824,
-                                    "self": 4.87605545005772,
+                                    "total": 28.704852470091282,
+                                    "count": 14322,
+                                    "self": 1.390311448074499,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 96.3633081798389,
-                                            "count": 48876,
-                                            "self": 21.483079906790408,
+                                            "total": 27.314541022016783,
+                                            "count": 13757,
+                                            "self": 6.127063125147288,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 74.88022827304849,
-                                                    "count": 48876,
-                                                    "self": 74.88022827304849
+                                                    "total": 21.187477896869495,
+                                                    "count": 13757,
+                                                    "self": 21.187477896869495
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.1311474799276766,
-                                    "count": 49823,
+                                    "total": 0.320556072947511,
+                                    "count": 14322,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2396.88050856301,
-                                            "count": 49823,
+                                            "total": 779.7088484159231,
+                                            "count": 14322,
                                             "is_parallel": true,
-                                            "self": 1122.0686625541803,
+                                            "self": 322.68404762594946,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -260,48 +260,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002752772999883746,
+                                                            "total": 0.0021394810000856523,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.001033865998579131,
+                                                            "self": 0.0006972569999561529,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0017189070013046148,
+                                                                    "total": 0.0014422240001294995,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0017189070013046148
+                                                                    "self": 0.0014422240001294995
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.0615624010006286,
+                                                            "total": 0.06311001700032648,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005867099998795311,
+                                                            "self": 0.0006312870018518879,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005159009997441899,
+                                                                    "total": 0.00048145399978238856,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005159009997441899
+                                                                    "self": 0.00048145399978238856
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.0584847690006427,
+                                                                    "total": 0.06000535999919521,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0584847690006427
+                                                                    "self": 0.06000535999919521
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.001975021000362176,
+                                                                    "total": 0.001991915999496996,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004616490004991647,
+                                                                    "self": 0.0004883079973296844,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0015133719998630113,
+                                                                            "total": 0.0015036080021673115,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0015133719998630113
+                                                                            "self": 0.0015036080021673115
                                                                         }
                                                                     }
                                                                 }
@@ -310,34 +310,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1274.81184600883,
-                                                    "count": 49822,
+                                                    "total": 457.0248007899736,
+                                                    "count": 14321,
                                                     "is_parallel": true,
-                                                    "self": 31.720769021942942,
+                                                    "self": 8.895754788175509,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 18.896137503044883,
-                                                            "count": 49822,
+                                                            "total": 5.460690289960439,
+                                                            "count": 14321,
                                                             "is_parallel": true,
-                                                            "self": 18.896137503044883
+                                                            "self": 5.460690289960439
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1117.4258751767757,
-                                                            "count": 49822,
+                                                            "total": 411.88394966486885,
+                                                            "count": 14321,
                                                             "is_parallel": true,
-                                                            "self": 1117.4258751767757
+                                                            "self": 411.88394966486885
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 106.7690643070664,
-                                                            "count": 49822,
+                                                            "total": 30.784406046968797,
+                                                            "count": 14321,
                                                             "is_parallel": true,
-                                                            "self": 24.16646897301598,
+                                                            "self": 7.581577122730778,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 82.60259533405042,
-                                                                    "count": 398576,
+                                                                    "total": 23.20282892423802,
+                                                                    "count": 114568,
                                                                     "is_parallel": true,
-                                                                    "self": 82.60259533405042
+                                                                    "self": 23.20282892423802
                                                                 }
                                                             }
                                                         }
@@ -350,31 +350,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 898.9074211980414,
-                            "count": 49823,
-                            "self": 3.0712260500840785,
+                            "total": 253.5065136518415,
+                            "count": 14322,
+                            "self": 0.9878365628892425,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 154.13215791196671,
-                                    "count": 49823,
-                                    "self": 154.0119976509659,
+                                    "total": 44.71119632395403,
+                                    "count": 14322,
+                                    "self": 44.50845595095507,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.12016026100081945,
+                                            "total": 0.20274037299896008,
                                             "count": 1,
-                                            "self": 0.12016026100081945
+                                            "self": 0.20274037299896008
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 741.7040372359907,
-                                    "count": 345,
-                                    "self": 194.08276745405965,
+                                    "total": 207.80748076499822,
+                                    "count": 103,
+                                    "self": 54.752951763956844,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 547.621269781931,
-                                            "count": 17811,
-                                            "self": 547.621269781931
+                                            "total": 153.05452900104137,
+                                            "count": 4962,
+                                            "self": 153.05452900104137
                                         }
                                     }
                                 }
@@ -383,19 +383,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.81299947143998e-06,
+                    "total": 2.2549993445863947e-06,
                     "count": 1,
-                    "self": 1.81299947143998e-06
+                    "self": 2.2549993445863947e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.18270244599989383,
+                    "total": 0.1775883749996865,
                     "count": 1,
-                    "self": 0.002395254999100871,
+                    "self": 0.007343440000113333,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.18030719100079295,
+                            "total": 0.17024493499957316,
                             "count": 1,
-                            "self": 0.18030719100079295
+                            "self": 0.17024493499957316
                         }
                     }
                 }

run_logs/training_status.json

@@ -18,15 +18,33 @@
                 "auxillary_file_paths": [
                     "results/Pyramids Training/Pyramids/Pyramids-780922.pt"
                 ]
+            },
+            {
+                "steps": 999951,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999951.onnx",
+                "reward": 1.310133305688699,
+                "creation_time": 1673947630.460905,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999951.pt"
+                ]
+            },
+            {
+                "steps": 1000079,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000079.onnx",
+                "reward": 1.310133305688699,
+                "creation_time": 1673947630.6682563,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000079.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 780922,
+            "steps": 1000079,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.6547499932348728,
-            "creation_time": 1673946819.2399633,
+            "reward": 1.310133305688699,
+            "creation_time": 1673947630.6682563,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-780922.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-1000079.pt"
             ]
         }
     },