First Push

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c45401a6680e69203bc0382269981b6a9dd9df54fc5be9c19468d2f0009e3e1
+oid sha256:f7abfeab0875ecf8ba95330c5f7018a40012a71643a951da3a82070e72e165e3
 size 1418184

Pyramids/Pyramids-1999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1adefcd5574795dbdc7896f24f941e1495f005e1db3813e1106703c938896d97
+size 1418184

Pyramids/Pyramids-1999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc14b33b9789a4da422df2e03f35ea8f4b74d24a10559239b462178b4ea9a8e
+size 8650990

Pyramids/Pyramids-2000001.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1adefcd5574795dbdc7896f24f941e1495f005e1db3813e1106703c938896d97
+size 1418184

Pyramids/Pyramids-2000001.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72761c7859f79862adf4d48e4d02c3c488a2df7904ee592fb3c86a38cc8091ab
+size 8650990

Pyramids/Pyramids-2060092.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7abfeab0875ecf8ba95330c5f7018a40012a71643a951da3a82070e72e165e3
+size 1418184

Pyramids/Pyramids-2060092.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802fa3852e9fc442f3bd06444d1463d0dcf4a6628a789bddc68c77f8866eb5d0
+size 8650990

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e6dbdc22ee56f2e882d555a2e9517c845bda8f51f1f4e3ab738275508139310
+oid sha256:802fa3852e9fc442f3bd06444d1463d0dcf4a6628a789bddc68c77f8866eb5d0
 size 8650990

Pyramids/events.out.tfevents.1688458060.e94e6c5a97bb.21326.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fe67795a9af3f25338a5f13dd8097afdcdd63ee90a847e0016eb3940165277f
+size 44897

Pyramids/events.out.tfevents.1688458625.e94e6c5a97bb.23779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c001cc05375cc5488e70ce0070abf7d60c281be0d44ad64ae0c92736300aa6c
+size 12734

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": 1800000, "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", "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": 2060000, "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", "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

@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1800000
+    max_steps: 2060000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -80,7 +80,7 @@ checkpoint_settings:
   run_id: Pyramids
   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] 55317 [Flags] 2 [Guid] 796719940 [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] 55147 [Flags] 2 [Guid] 694174503 [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  0.091 seconds
+- Completed reload, in  0.094 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: 0.791429 ms
+UnloadTime: 0.802427 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]: 6122 frames, [32.0 KB-64.0 KB]: 19112 frames, [64.0 KB-128.0 KB]: 8534 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 125 frames, [32.0 KB-64.0 KB]: 587 frames, [64.0 KB-128.0 KB]: 429 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -131,12 +128,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
+    [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 7]
+    [ALLOC_TEMP_Background Job.Worker 15]
       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]: 33470 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 29 frames, [1.0 MB-2.0 MB]: 1113 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 12072
+  Peak main deferred allocation count 9430
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 33768 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 1141 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.7 MB
+      Peak Block count 2
+      Peak Allocated memory 22.3 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 33769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1142 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 24.0 MB
+      Peak Allocated memory 22.9 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -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 1.3 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 33768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1141 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]: 33769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1142 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 1.3 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 33470 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 33 frames, [1.0 MB-2.0 MB]: 1109 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]: 33768 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1141 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
@@ -291,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.3 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 33769 frames
+      Peak usage frame count: [0-1.0 KB]: 1142 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]: 33769 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1142 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]: 33769 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 1142 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.2 KB
+  Peak Allocated memory 27.4 KB
   Peak Large allocation bytes 0 B
     [ALLOC_PROFILER_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1688457788923,"processId":2344,"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":1688458790074,"processId":23797,"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": 0.1715385615825653,
-            "min": 0.16655592620372772,
-            "max": 1.421165943145752,
-            "count": 60
+            "value": 0.16006402671337128,
+            "min": 0.156986802816391,
+            "max": 0.16006402671337128,
+            "count": 2
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 5173.60302734375,
-            "min": 5023.32666015625,
-            "max": 43112.48828125,
-            "count": 60
+            "value": 4814.72607421875,
+            "min": 1695.45751953125,
+            "max": 4814.72607421875,
+            "count": 2
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 234.7795275590551,
+            "min": 191.93333333333334,
+            "max": 234.7795275590551,
+            "count": 2
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29817.0,
+            "min": 8637.0,
+            "max": 29817.0,
+            "count": 2
         },
         "Pyramids.Step.mean": {
-            "value": 1799992.0,
-            "min": 29952.0,
-            "max": 1799992.0,
-            "count": 60
+            "value": 2039950.0,
+            "min": 2009981.0,
+            "max": 2039950.0,
+            "count": 2
         },
         "Pyramids.Step.sum": {
-            "value": 1799992.0,
-            "min": 29952.0,
-            "max": 1799992.0,
-            "count": 60
+            "value": 2039950.0,
+            "min": 2009981.0,
+            "max": 2039950.0,
+            "count": 2
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.782856822013855,
-            "min": -0.09550127387046814,
-            "max": 0.7982697486877441,
-            "count": 60
+            "value": 0.7881335020065308,
+            "min": 0.7869158983230591,
+            "max": 0.7881335020065308,
+            "count": 2
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 231.72561645507812,
-            "min": -23.111309051513672,
-            "max": 236.287841796875,
-            "count": 60
+            "value": 234.07565307617188,
+            "min": 76.33084106445312,
+            "max": 234.07565307617188,
+            "count": 2
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.05314372852444649,
-            "min": 0.0006669824360869825,
-            "max": 0.3885059356689453,
-            "count": 60
+            "value": 0.014494973234832287,
+            "min": 0.014494973234832287,
+            "max": 0.01644633524119854,
+            "count": 2
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 15.730544090270996,
-            "min": 0.1880890429019928,
-            "max": 92.0759048461914,
-            "count": 60
+            "value": 4.305006980895996,
+            "min": 1.59529447555542,
+            "max": 4.305006980895996,
+            "count": 2
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.735530696339964,
+            "min": 1.735530696339964,
+            "max": 1.8061818080869587,
+            "count": 2
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 220.41239843517542,
+            "min": 79.47199955582619,
+            "max": 220.41239843517542,
+            "count": 2
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.735530696339964,
+            "min": 1.735530696339964,
+            "max": 1.8061818080869587,
+            "count": 2
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 220.41239843517542,
+            "min": 79.47199955582619,
+            "max": 220.41239843517542,
+            "count": 2
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.018833197139507877,
+            "min": 0.016944439728500914,
+            "max": 0.018833197139507877,
+            "count": 2
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.3918160367175005,
+            "min": 0.7455553480540402,
+            "max": 2.3918160367175005,
+            "count": 2
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06692209870347546,
-            "min": 0.065360669164034,
-            "max": 0.07420832000362051,
-            "count": 60
+            "value": 0.06691430932412566,
+            "min": 0.06691430932412566,
+            "max": 0.07264888364685855,
+            "count": 2
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 1.0038314805521318,
-            "min": 0.49306459753889853,
-            "max": 1.072577590442961,
-            "count": 60
+            "value": 0.9368003305377592,
+            "min": 0.2905955345874342,
+            "max": 0.9368003305377592,
+            "count": 2
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.013719577577042702,
-            "min": 0.0009919393017094116,
-            "max": 0.017079275870249454,
-            "count": 60
+            "value": 0.014317989454693383,
+            "min": 0.014317989454693383,
+            "max": 0.01548235956579447,
+            "count": 2
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.20579366365564053,
-            "min": 0.0069435751119658815,
-            "max": 0.24374312801713435,
-            "count": 60
+            "value": 0.20045185236570737,
+            "min": 0.06192943826317788,
+            "max": 0.20045185236570737,
+            "count": 2
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 2.5408880419592553e-06,
-            "min": 2.5408880419592553e-06,
-            "max": 0.00029730590565993657,
-            "count": 60
+            "value": 5.216530300024272e-06,
+            "min": 5.216530300024272e-06,
+            "max": 7.982827921614084e-06,
+            "count": 2
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 3.811332062938883e-05,
-            "min": 3.811332062938883e-05,
-            "max": 0.003815351794882777,
-            "count": 60
+            "value": 7.303142420033981e-05,
+            "min": 3.193131168645634e-05,
+            "max": 7.303142420033981e-05,
+            "count": 2
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10084692962962961,
-            "min": 0.10084692962962961,
-            "max": 0.19910196825396828,
-            "count": 60
+            "value": 0.10173881067961164,
+            "min": 0.10173881067961164,
+            "max": 0.10266091019417477,
+            "count": 2
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5127039444444441,
-            "min": 1.382840888888889,
-            "max": 2.6717838888888896,
-            "count": 60
+            "value": 1.424343349514563,
+            "min": 0.41064364077669907,
+            "max": 1.424343349514563,
+            "count": 2
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 9.460826999999987e-05,
-            "min": 9.460826999999987e-05,
-            "max": 0.00991028662857143,
-            "count": 60
+            "value": 0.00018370718689320387,
+            "min": 0.00018370718689320387,
+            "max": 0.0002758249283980585,
+            "count": 2
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.001419124049999998,
-            "min": 0.001419124049999998,
-            "max": 0.12719121049999998,
-            "count": 60
+            "value": 0.0025719006165048543,
+            "min": 0.001103299713592234,
+            "max": 0.0025719006165048543,
+            "count": 2
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.00832408294081688,
-            "min": 0.00832408294081688,
-            "max": 0.6539134979248047,
-            "count": 60
+            "value": 0.007855918258428574,
+            "min": 0.007855918258428574,
+            "max": 0.00804874673485756,
+            "count": 2
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.12486124038696289,
-            "min": 0.11776343733072281,
-            "max": 4.577394485473633,
-            "count": 60
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 249.4308943089431,
-            "min": 225.359375,
-            "max": 999.0,
-            "count": 60
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30680.0,
-            "min": 15984.0,
-            "max": 32497.0,
-            "count": 60
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.718191783875227,
-            "min": -1.0000000521540642,
-            "max": 1.7748992145061493,
-            "count": 60
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 209.6193976327777,
-            "min": -32.000001668930054,
-            "max": 234.07499803602695,
-            "count": 60
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.718191783875227,
-            "min": -1.0000000521540642,
-            "max": 1.7748992145061493,
-            "count": 60
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 209.6193976327777,
-            "min": -32.000001668930054,
-            "max": 234.07499803602695,
-            "count": 60
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.021272506244474885,
-            "min": 0.01995797076577487,
-            "max": 13.963886933401227,
-            "count": 60
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 2.595245761825936,
-            "min": 2.574578228784958,
-            "max": 223.42219093441963,
-            "count": 60
+            "value": 0.10998285561800003,
+            "min": 0.03219498693943024,
+            "max": 0.10998285561800003,
+            "count": 2
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 60
+            "count": 2
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 60
+            "count": 2
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1688453477",
+        "start_time_seconds": "1688458624",
         "python_version": "3.10.12 (main, Jun  7 2023, 12:45:35) [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 --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids --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": "1688457788"
+        "end_time_seconds": "1688458790"
     },
-    "total": 4311.33834147,
+    "total": 165.3351730230006,
     "count": 1,
-    "self": 0.4928945660003592,
+    "self": 0.48259728100128996,
     "children": {
         "run_training.setup": {
-            "total": 0.040185014000030606,
+            "total": 0.04126745499979734,
             "count": 1,
-            "self": 0.040185014000030606
+            "self": 0.04126745499979734
         },
         "TrainerController.start_learning": {
-            "total": 4310.80526189,
+            "total": 164.81130828699952,
             "count": 1,
-            "self": 2.2454665520026538,
+            "self": 0.07856928099772631,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 4.229319896999982,
+                    "total": 5.059011301999817,
                     "count": 1,
-                    "self": 4.229319896999982
+                    "self": 5.059011301999817
                 },
                 "TrainerController.advance": {
-                    "total": 4304.235217063997,
-                    "count": 116536,
-                    "self": 2.3751496051863796,
+                    "total": 159.55792486200244,
+                    "count": 4008,
+                    "self": 0.08047015601277963,
                     "children": {
                         "env_step": {
-                            "total": 3177.9921760129196,
-                            "count": 116536,
-                            "self": 2990.0624195820574,
+                            "total": 122.07408524198672,
+                            "count": 4008,
+                            "self": 115.64559847698911,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 186.57838026592447,
-                                    "count": 116536,
-                                    "self": 8.130507214897193,
+                                    "total": 6.381658935021733,
+                                    "count": 4008,
+                                    "self": 0.2825198660229944,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 178.44787305102727,
-                                            "count": 112562,
-                                            "self": 178.44787305102727
+                                            "total": 6.099139068998738,
+                                            "count": 3806,
+                                            "self": 6.099139068998738
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 1.351376164937733,
-                                    "count": 116536,
+                                    "total": 0.046827829975882196,
+                                    "count": 4008,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4301.489238747982,
-                                            "count": 116536,
+                                            "total": 164.38459658699776,
+                                            "count": 4008,
                                             "is_parallel": true,
-                                            "self": 1510.2127382340072,
+                                            "self": 55.86290461896624,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.004985786000020198,
+                                                            "total": 0.001749106000715983,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0036836550000316493,
+                                                            "self": 0.0005427510013760184,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0013021309999885489,
+                                                                    "total": 0.0012063549993399647,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0013021309999885489
+                                                                    "self": 0.0012063549993399647
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.048076196000010896,
+                                                            "total": 0.08569502299997112,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0005786460001218074,
+                                                            "self": 0.0005558439997912501,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004814179999357293,
+                                                                    "total": 0.0005375700002332451,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004814179999357293
+                                                                    "self": 0.0005375700002332451
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04529628800003138,
+                                                                    "total": 0.08276233699962177,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04529628800003138
+                                                                    "self": 0.08276233699962177
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0017198439999219772,
+                                                                    "total": 0.0018392720003248542,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003412150000485781,
+                                                                    "self": 0.00037271300243446603,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0013786289998733992,
+                                                                            "total": 0.0014665589978903881,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0013786289998733992
+                                                                            "self": 0.0014665589978903881
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 2791.276500513975,
-                                                    "count": 116535,
+                                                    "total": 108.52169196803152,
+                                                    "count": 4007,
                                                     "is_parallel": true,
-                                                    "self": 59.602570526089494,
+                                                    "self": 2.0542488840337683,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 40.586966729973824,
-                                                            "count": 116535,
+                                                            "total": 1.3711916139900495,
+                                                            "count": 4007,
                                                             "is_parallel": true,
-                                                            "self": 40.586966729973824
+                                                            "self": 1.3711916139900495
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 2512.7897777189764,
-                                                            "count": 116535,
+                                                            "total": 98.87827676101642,
+                                                            "count": 4007,
                                                             "is_parallel": true,
-                                                            "self": 2512.7897777189764
+                                                            "self": 98.87827676101642
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 178.29718553893508,
-                                                            "count": 116535,
+                                                            "total": 6.217974708991278,
+                                                            "count": 4007,
                                                             "is_parallel": true,
-                                                            "self": 34.51629501789773,
+                                                            "self": 1.2065338049815182,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 143.78089052103735,
-                                                                    "count": 932280,
+                                                                    "total": 5.01144090400976,
+                                                                    "count": 32056,
                                                                     "is_parallel": true,
-                                                                    "self": 143.78089052103735
+                                                                    "self": 5.01144090400976
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,24 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1123.8678914458906,
-                            "count": 116536,
-                            "self": 4.584832678865496,
+                            "total": 37.403369464002935,
+                            "count": 4008,
+                            "self": 0.15981210298377846,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 194.21868595102057,
-                                    "count": 116536,
-                                    "self": 193.91623728402044,
-                                    "children": {
-                                        "RLTrainer._checkpoint": {
-                                            "total": 0.3024486670001352,
-                                            "count": 3,
-                                            "self": 0.3024486670001352
-                                        }
-                                    }
+                                    "total": 6.524042991019996,
+                                    "count": 4008,
+                                    "self": 6.524042991019996
                                 },
                                 "_update_policy": {
-                                    "total": 925.0643728160044,
-                                    "count": 829,
-                                    "self": 591.7764752618816,
+                                    "total": 30.71951436999916,
+                                    "count": 28,
+                                    "self": 19.815611368988357,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 333.28789755412276,
-                                            "count": 41025,
-                                            "self": 333.28789755412276
+                                            "total": 10.903903001010804,
+                                            "count": 1344,
+                                            "self": 10.903903001010804
                                         }
                                     }
                                 }
@@ -376,19 +369,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 9.34000127017498e-07,
+                    "total": 9.90999978967011e-07,
                     "count": 1,
-                    "self": 9.34000127017498e-07
+                    "self": 9.90999978967011e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09525744300026417,
+                    "total": 0.11580185099955997,
                     "count": 1,
-                    "self": 0.0013838309996572207,
+                    "self": 0.0017628519990466884,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09387361200060695,
+                            "total": 0.11403899900051329,
                             "count": 1,
-                            "self": 0.09387361200060695
+                            "self": 0.11403899900051329
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,24 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499878,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-499878.onnx",
-                "reward": 0.8186499886214733,
-                "creation_time": 1688454466.9037788,
-                "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-499878.pt"
-                ]
-            },
-            {
-                "steps": 999939,
-                "file_path": "results/Pyramids/Pyramids/Pyramids-999939.onnx",
-                "reward": null,
-                "creation_time": 1688455703.2320125,
-                "auxillary_file_paths": [
-                    "results/Pyramids/Pyramids/Pyramids-999939.pt"
-                ]
-            },
             {
                 "steps": 1499911,
                 "file_path": "results/Pyramids/Pyramids/Pyramids-1499911.onnx",
@@ -36,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids/Pyramids/Pyramids-1800038.pt"
                 ]
+            },
+            {
+                "steps": 1999972,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-1999972.onnx",
+                "reward": 1.728285693696567,
+                "creation_time": 1688458591.2445402,
+                "auxillary_file_paths": [
+                    "results/Pyramids/Pyramids/Pyramids-1999972.pt"
+                ]
+            },
+            {
+                "steps": 2000001,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-2000001.onnx",
+                "reward": 1.7267499808222055,
+                "creation_time": 1688458591.3466892,
+                "auxillary_file_paths": [
+                    "results/Pyramids/Pyramids/Pyramids-2000001.pt"
+                ]
+            },
+            {
+                "steps": 2060092,
+                "file_path": "results/Pyramids/Pyramids/Pyramids-2060092.onnx",
+                "reward": 1.7506666382153828,
+                "creation_time": 1688458789.6562772,
+                "auxillary_file_paths": [
+                    "results/Pyramids/Pyramids/Pyramids-2060092.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1800038,
+            "steps": 2060092,
             "file_path": "results/Pyramids/Pyramids.onnx",
-            "reward": 1.806500032544136,
-            "creation_time": 1688457788.487128,
+            "reward": 1.7506666382153828,
+            "creation_time": 1688458789.6562772,
             "auxillary_file_paths": [
-                "results/Pyramids/Pyramids/Pyramids-1800038.pt"
+                "results/Pyramids/Pyramids/Pyramids-2060092.pt"
             ]
         }
     },