secondPush

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa2dbd767533677ce92d7a17a30f977bc4c4a8fcfd6bdc60e5ef94126b8c93b
+oid sha256:515cde81eda838b644a44462d860936cfe31c93d691af91f6abd63e9a1865003
 size 1420238

Pyramids/Pyramids-1499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d155c305fc57800a4680c2eba548d273c7500b7101911681c351409d1553a0
+size 1420238

Pyramids/Pyramids-1499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e70f343b214e5886a4144eb709c9114cdcba26c8dc5632c6ab7aab24cce820d9
+size 8656252

Pyramids/Pyramids-1999876.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515cde81eda838b644a44462d860936cfe31c93d691af91f6abd63e9a1865003
+size 1420238

Pyramids/Pyramids-1999876.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed3dcb03f4a056e6df26227d2eaa340dc1f393307cf742b9f66b4d3ac350c71
+size 8656252

Pyramids/Pyramids-2000132.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515cde81eda838b644a44462d860936cfe31c93d691af91f6abd63e9a1865003
+size 1420238

Pyramids/Pyramids-2000132.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b903c9fc265b17975f536b1e331d0bc15efee6a3927788a6ce2ef3a5831508
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4d6d84b2b0a19b3123e9bf6ff9794848bb65d3df000d40ea259724c1984fa2d
+oid sha256:65f210eef014f6b1dfe7521f46d69d7450eb0f0849d1360fbd035f116cf6acf7
 size 8655778

Pyramids/events.out.tfevents.1715156228.62d38fe906b4.22872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82c795c25276e280f8331000e690d170fcf4465bd0cc82d3b4ab3ce2c7db2da
+size 1423

Pyramids/events.out.tfevents.1715156389.62d38fe906b4.23614.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8587f8eacf83c10807e2a9bf2d18bf245ac79ef7852c78468229f32ef994e38a
+size 324356

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.05, "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": 2000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -6,7 +6,7 @@ behaviors:
       batch_size: 128
       buffer_size: 2048
       learning_rate: 0.0003
-      beta: 0.01
+      beta: 0.05
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
@@ -51,7 +51,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 1000000
+    max_steps: 2000000
     time_horizon: 128
     summary_freq: 30000
     threaded: false
@@ -82,7 +82,7 @@ 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/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/content/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] 55144 [Flags] 2 [Guid] 3721749209 [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] 55193 [Flags] 2 [Guid] 2374015505 [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/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -36,7 +33,7 @@ ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.143 seconds
+- Completed reload, in  0.139 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -68,7 +65,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 1.093438 ms
+UnloadTime: 0.851181 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]: 9068 frames, [32.0 KB-64.0 KB]: 7874 frames, [64.0 KB-128.0 KB]: 1825 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2163 frames, [32.0 KB-64.0 KB]: 11981 frames, [64.0 KB-128.0 KB]: 4620 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
@@ -149,7 +146,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 480 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -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]: 18469 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 113 frames, [1.0 MB-2.0 MB]: 18652 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.6 MB
+  Peak Allocated memory 1.2 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 11813
+  Peak main deferred allocation count 12230
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18767 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18764 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 30.6 MB
+      Peak Block count 2
+      Peak Allocated memory 24.5 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.4 MB
+      Peak Allocated memory 21.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -255,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18767 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 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]: 18768 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18765 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -273,45 +270,45 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18469 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 128 frames, [1.0 MB-2.0 MB]: 18637 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]: 18767 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
       Requested Block Size 4.0 MB
-      Peak Block count 1
-      Peak Allocated memory 3.9 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 1.7 MB
+      Peak Allocated bytes 1.5 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18768 frames
+      Peak usage frame count: [0-1.0 KB]: 18765 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]: 18768 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18765 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]: 18768 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18765 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 28.6 KB
+  Peak Allocated memory 29.0 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":1715154724940,"processId":7043,"allocatedMemory":1970103,"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":3417},{"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":1715158946927,"processId":23651,"allocatedMemory":1970103,"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":3417},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -2,171 +2,171 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.6039745211601257,
-            "min": 0.6000012159347534,
-            "max": 1.436845302581787,
+            "value": 0.6050494909286499,
+            "min": 0.6050494909286499,
+            "max": 0.8366415500640869,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 18080.58203125,
-            "min": 18080.58203125,
-            "max": 43588.140625,
+            "value": 18093.400390625,
+            "min": 12879.2548828125,
+            "max": 25483.14453125,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989947.0,
-            "min": 29952.0,
-            "max": 989947.0,
+            "value": 1979883.0,
+            "min": 1019966.0,
+            "max": 1979883.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989947.0,
-            "min": 29952.0,
-            "max": 989947.0,
+            "value": 1979883.0,
+            "min": 1019966.0,
+            "max": 1979883.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.22127962112426758,
-            "min": -0.14240340888500214,
-            "max": 0.22692649066448212,
+            "value": 0.62385094165802,
+            "min": 0.21211732923984528,
+            "max": 0.6899233460426331,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 56.6475830078125,
-            "min": -34.46162414550781,
-            "max": 56.95854949951172,
+            "value": 177.79751586914062,
+            "min": 34.999359130859375,
+            "max": 194.5907745361328,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.009353633970022202,
-            "min": -0.009353633970022202,
-            "max": 0.27930352091789246,
+            "value": 0.018732663244009018,
+            "min": -0.016395842656493187,
+            "max": 0.02733149379491806,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -2.3945302963256836,
-            "min": -2.3945302963256836,
-            "max": 67.87075805664062,
+            "value": 5.338809013366699,
+            "min": -2.7053141593933105,
+            "max": 7.570823669433594,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.07019824544274371,
-            "min": 0.06501774602292135,
-            "max": 0.07107800641528118,
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 274.0571428571429,
+            "min": 260.8256880733945,
+            "max": 702.4090909090909,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9827754361984119,
-            "min": 0.497193543908478,
-            "max": 1.0575461518806955,
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28776.0,
+            "min": 15453.0,
+            "max": 31444.0,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.009200069713187986,
-            "min": 9.248179810969358e-05,
-            "max": 0.010453219176189224,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6687866522442727,
+            "min": 0.7518635967915709,
+            "max": 1.716990372739159,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.1288009759846318,
-            "min": 0.00129474517353571,
-            "max": 0.15679828764283837,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 175.22259848564863,
+            "min": 16.54099912941456,
+            "max": 185.8733986467123,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.477768936014285e-06,
-            "min": 7.477768936014285e-06,
-            "max": 0.00029515063018788575,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6687866522442727,
+            "min": 0.7518635967915709,
+            "max": 1.716990372739159,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010468876510419999,
-            "min": 0.00010468876510419999,
-            "max": 0.003507862130712699,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 175.22259848564863,
+            "min": 16.54099912941456,
+            "max": 185.8733986467123,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10249255714285717,
-            "min": 0.10249255714285717,
-            "max": 0.19838354285714285,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02576101848667133,
+            "min": 0.023524496236008618,
+            "max": 0.08017137258800423,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.4348958000000003,
-            "min": 1.3886848,
-            "max": 2.5692873000000005,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.7049069411004893,
+            "min": 1.7637701969360933,
+            "max": 3.418516769306734,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.0002590064585714286,
-            "min": 0.0002590064585714286,
-            "max": 0.00983851593142857,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06855222881477814,
+            "min": 0.06581879631201712,
+            "max": 0.07266657747234041,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.0036260904200000007,
-            "min": 0.0036260904200000007,
-            "max": 0.11695180126999999,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.959731203406894,
+            "min": 0.6165068184463801,
+            "max": 1.0516260387569978,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.011281010694801807,
-            "min": 0.011281010694801807,
-            "max": 0.418881356716156,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014468770938817346,
+            "min": 0.007192014726918317,
+            "max": 0.015923273303390793,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.15793414413928986,
-            "min": 0.15793414413928986,
-            "max": 2.9321694374084473,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.20256279314344283,
+            "min": 0.06472813254226485,
+            "max": 0.23874681045708715,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 639.3921568627451,
-            "min": 617.5625,
-            "max": 999.0,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.1469839986571415e-06,
+            "min": 5.1469839986571415e-06,
+            "max": 0.00014839503386833888,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 32609.0,
-            "min": 15984.0,
-            "max": 32937.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.205777598119998e-05,
+            "min": 7.205777598119998e-05,
+            "max": 0.0020257139747622502,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.844359967559576,
-            "min": -1.0000000521540642,
-            "max": 0.844359967559576,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10171562857142857,
+            "min": 0.10171562857142857,
+            "max": 0.14946499444444444,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 42.2179983779788,
-            "min": -29.92220164835453,
-            "max": 42.2179983779788,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4240188,
+            "min": 1.34518495,
+            "max": 2.1564492000000004,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.844359967559576,
-            "min": -1.0000000521540642,
-            "max": 0.844359967559576,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0008676427228571425,
+            "min": 0.0008676427228571425,
+            "max": 0.02473755072277778,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 42.2179983779788,
-            "min": -29.92220164835453,
-            "max": 42.2179983779788,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.012146998119999995,
+            "min": 0.012146998119999995,
+            "max": 0.33769135122499994,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.07614177400246262,
-            "min": 0.07614177400246262,
-            "max": 7.93699399009347,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.008959934115409851,
+            "min": 0.00835987739264965,
+            "max": 0.01113196648657322,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.8070887001231313,
-            "min": 3.736620957381092,
-            "max": 126.99190384149551,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.12543907761573792,
+            "min": 0.0981353372335434,
+            "max": 0.15584753453731537,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1715152486",
+        "start_time_seconds": "1715156388",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/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 ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1715154725"
+        "end_time_seconds": "1715158946"
     },
-    "total": 2238.277268734,
+    "total": 2558.318411821,
     "count": 1,
-    "self": 0.537508945999889,
+    "self": 0.4771156560000236,
     "children": {
         "run_training.setup": {
-            "total": 0.08579748800002562,
+            "total": 0.051621190999867395,
             "count": 1,
-            "self": 0.08579748800002562
+            "self": 0.051621190999867395
         },
         "TrainerController.start_learning": {
-            "total": 2237.6539623,
+            "total": 2557.7896749740003,
             "count": 1,
-            "self": 1.3867645539471596,
+            "self": 1.5009321149082098,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.6186888519998774,
+                    "total": 2.1861396180001975,
                     "count": 1,
-                    "self": 2.6186888519998774
+                    "self": 2.1861396180001975
                 },
                 "TrainerController.advance": {
-                    "total": 2233.5538953500536,
-                    "count": 63343,
-                    "self": 1.4693391541086385,
+                    "total": 2554.007595873092,
+                    "count": 64646,
+                    "self": 1.5691814611809605,
                     "children": {
                         "env_step": {
-                            "total": 1560.1188904520081,
-                            "count": 63343,
-                            "self": 1419.1651280929682,
+                            "total": 1868.7834362149733,
+                            "count": 64646,
+                            "self": 1727.1443113118885,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 140.07365237900854,
-                                    "count": 63343,
-                                    "self": 5.028751032045193,
+                                    "total": 140.72589767201407,
+                                    "count": 64646,
+                                    "self": 5.442068254879814,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 135.04490134696334,
-                                            "count": 62558,
-                                            "self": 135.04490134696334
+                                            "total": 135.28382941713426,
+                                            "count": 62549,
+                                            "self": 135.28382941713426
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8801099800314205,
-                                    "count": 63343,
+                                    "total": 0.9132272310707776,
+                                    "count": 64646,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2232.5542327740595,
-                                            "count": 63343,
+                                            "total": 2551.910830787956,
+                                            "count": 64646,
                                             "is_parallel": true,
-                                            "self": 945.3859805850675,
+                                            "self": 963.0787922048903,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002975676999994903,
+                                                            "total": 0.002196669999648293,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008085409997420356,
+                                                            "self": 0.0006604640002478845,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0021671360002528672,
+                                                                    "total": 0.0015362059994004085,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0021671360002528672
+                                                                    "self": 0.0015362059994004085
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05488367800012384,
+                                                            "total": 0.05332669800009171,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007848100003684522,
+                                                            "self": 0.0007138900009522331,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0005150899999080139,
+                                                                    "total": 0.000479559999803314,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005150899999080139
+                                                                    "self": 0.000479559999803314
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05172547699999086,
+                                                                    "total": 0.05028351399960229,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05172547699999086
+                                                                    "self": 0.05028351399960229
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0018583009998565103,
+                                                                    "total": 0.0018497339997338713,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00038718699966011627,
+                                                                    "self": 0.00036156599890091456,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001471114000196394,
+                                                                            "total": 0.0014881680008329567,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001471114000196394
+                                                                            "self": 0.0014881680008329567
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1287.168252188992,
-                                                    "count": 63342,
+                                                    "total": 1588.8320385830657,
+                                                    "count": 64645,
                                                     "is_parallel": true,
-                                                    "self": 35.95679009294918,
+                                                    "self": 36.778021791972606,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 26.421660601010444,
-                                                            "count": 63342,
+                                                            "total": 26.658363137064953,
+                                                            "count": 64645,
                                                             "is_parallel": true,
-                                                            "self": 26.421660601010444
+                                                            "self": 26.658363137064953
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1115.4136403839632,
-                                                            "count": 63342,
+                                                            "total": 1413.5190357680112,
+                                                            "count": 64645,
                                                             "is_parallel": true,
-                                                            "self": 1115.4136403839632
+                                                            "self": 1413.5190357680112
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 109.37616111106922,
-                                                            "count": 63342,
+                                                            "total": 111.8766178860169,
+                                                            "count": 64645,
                                                             "is_parallel": true,
-                                                            "self": 22.61427519700237,
+                                                            "self": 23.183875133140646,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 86.76188591406685,
-                                                                    "count": 506736,
+                                                                    "total": 88.69274275287626,
+                                                                    "count": 517160,
                                                                     "is_parallel": true,
-                                                                    "self": 86.76188591406685
+                                                                    "self": 88.69274275287626
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 671.965665743937,
-                            "count": 63343,
-                            "self": 2.676080602944239,
+                            "total": 683.6549781969379,
+                            "count": 64646,
+                            "self": 2.9432743299876165,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 136.93201416998932,
-                                    "count": 63343,
-                                    "self": 136.71975104898934,
+                                    "total": 145.74747356994885,
+                                    "count": 64646,
+                                    "self": 145.46585365194915,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.21226312099997813,
+                                            "total": 0.28161991799970565,
                                             "count": 2,
-                                            "self": 0.21226312099997813
+                                            "self": 0.28161991799970565
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 532.3575709710035,
-                                    "count": 454,
-                                    "self": 317.7516855590418,
+                                    "total": 534.9642302970014,
+                                    "count": 473,
+                                    "self": 317.0337109129723,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 214.6058854119617,
-                                            "count": 22845,
-                                            "self": 214.6058854119617
+                                            "total": 217.93051938402914,
+                                            "count": 22764,
+                                            "self": 217.93051938402914
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0139997357327957e-06,
+                    "total": 1.0049998309114017e-06,
                     "count": 1,
-                    "self": 1.0139997357327957e-06
+                    "self": 1.0049998309114017e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.09461252999972203,
+                    "total": 0.09500636299981124,
                     "count": 1,
-                    "self": 0.0015217529994515644,
+                    "self": 0.002084752999508055,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.09309077700027046,
+                            "total": 0.09292161000030319,
                             "count": 1,
-                            "self": 0.09309077700027046
+                            "self": 0.09292161000030319
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,40 +2,58 @@
     "Pyramids": {
         "checkpoints": [
             {
-                "steps": 499931,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499931.onnx",
-                "reward": 1.3530000001192093,
-                "creation_time": 1715153556.5386198,
+                "steps": 1000011,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000011.onnx",
+                "reward": 1.7090000212192535,
+                "creation_time": 1715154724.4615238,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-499931.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
                 ]
             },
             {
-                "steps": 999975,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999975.onnx",
+                "steps": 1000011,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000011.onnx",
                 "reward": null,
-                "creation_time": 1715154724.3618088,
+                "creation_time": 1715156230.1494763,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-999975.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
                 ]
             },
             {
-                "steps": 1000011,
-                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000011.onnx",
-                "reward": 1.7090000212192535,
-                "creation_time": 1715154724.4615238,
+                "steps": 1499912,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499912.onnx",
+                "reward": 1.6379999816417694,
+                "creation_time": 1715157631.2885382,
                 "auxillary_file_paths": [
-                    "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
+                    "results/Pyramids Training/Pyramids/Pyramids-1499912.pt"
+                ]
+            },
+            {
+                "steps": 1999876,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999876.onnx",
+                "reward": 1.615799966454506,
+                "creation_time": 1715158946.3542082,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999876.pt"
+                ]
+            },
+            {
+                "steps": 2000132,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2000132.onnx",
+                "reward": 1.615799966454506,
+                "creation_time": 1715158946.47209,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2000132.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000011,
+            "steps": 2000132,
             "file_path": "results/Pyramids Training/Pyramids.onnx",
-            "reward": 1.7090000212192535,
-            "creation_time": 1715154724.4615238,
+            "reward": 1.615799966454506,
+            "creation_time": 1715158946.47209,
             "auxillary_file_paths": [
-                "results/Pyramids Training/Pyramids/Pyramids-1000011.pt"
+                "results/Pyramids Training/Pyramids/Pyramids-2000132.pt"
             ]
         }
     },