continue to 3M

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3283343e69365de6eb7ec705cb67d4efb0ea9a060791d7db5144262d7bd5386
+oid sha256:3043a5ce54d7c7ab6ea2e187747ffed5e907a79a1a7374d8a642752a7eba3657
 size 1420238

Pyramids/Pyramids-2010391.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d430a6106f7fa3333eaf4bb5cf7b32e51a780e72baf4d002d3bcfc58c4934f
+size 1420238

Pyramids/Pyramids-2010391.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7af90a45d585f6aabb538dc7c84e96df3682b9b91c12188849b23629907f443
+size 8656252

Pyramids/Pyramids-2499940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3214e218c87b626fef6cd38b12d92a61c9b53fbaffbd98f28eed9827351d12ff
+size 1420238

Pyramids/Pyramids-2499940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887cd6206d8284bb1e7385809ac686d500acf62509d25401c6c6046cb1d23f20
+size 8656252

Pyramids/Pyramids-2999881.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3043a5ce54d7c7ab6ea2e187747ffed5e907a79a1a7374d8a642752a7eba3657
+size 1420238

Pyramids/Pyramids-2999881.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f33e27f544982350488c92bab1a39d3fa0b8de4d4cc286be3c425322ff879ca
+size 8656252

Pyramids/Pyramids-3000009.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3043a5ce54d7c7ab6ea2e187747ffed5e907a79a1a7374d8a642752a7eba3657
+size 1420238

Pyramids/Pyramids-3000009.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da3f42feb20d5c6ba8ad4b6ddf0518b87192431dee83e9e45cc5e247be5b692f
+size 8656252

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61dd5010eae58f7db3bbc54652d20591c0a0d995b0204a4e3d2742872444cc63
+oid sha256:a0cd445432f806bb16cf47e280f5bf0d0ba28c1a11451454462d258c64b67973
 size 8655778

Pyramids/events.out.tfevents.1732218458.02aa6a4a6e33.31553.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f3678bbfee378e0b38a0eb5b34a4935160f1640855af2ee322672e27e02b5b
+size 2406

Pyramids/events.out.tfevents.1732218521.02aa6a4a6e33.31898.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b1ba00dd45db09065ae4681a50034918ecd9356fe17bda2accd1cc6d7c61ff
+size 737575

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": 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": "PyramidsTraining", "initialize_from": null, "load_model": false, "resume": true, "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": 10, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 10000, "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": "PyramidsTraining", "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

@@ -49,11 +49,11 @@ behaviors:
         learning_rate: 0.0001
         encoding_size: null
     init_path: null
-    keep_checkpoints: 5
+    keep_checkpoints: 10
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 128
-    summary_freq: 30000
+    summary_freq: 10000
     threaded: false
     self_play: null
     behavioral_cloning: null

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 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] 55435 [Flags] 2 [Guid] 1748520219 [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] 55262 [Flags] 2 [Guid] 2622568142 [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'
 Initialize engine version: 2021.3.5f1 (40eb3a945986)
@@ -33,7 +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  0.095 seconds
+- Completed reload, in  0.090 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)
@@ -65,7 +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: 0.782758 ms
+UnloadTime: 0.827180 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.
@@ -73,7 +73,7 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 2615 frames, [32.0 KB-64.0 KB]: 12789 frames, [64.0 KB-128.0 KB]: 3361 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2974 frames, [32.0 KB-64.0 KB]: 10486 frames, [64.0 KB-128.0 KB]: 5115 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
@@ -146,7 +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 240 B
       Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
@@ -204,28 +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]: 90 frames, [1.0 MB-2.0 MB]: 18676 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 51 frames, [1.0 MB-2.0 MB]: 18525 frames
   Requested Block Size 1.0 MB
   Peak Block count 2
-  Peak Allocated memory 1.3 MB
+  Peak Allocated memory 1.1 MB
   Peak Large allocation bytes 0 B
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 13122
+  Peak main deferred allocation count 10354
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18765 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 3 frames, [16.0 MB-32.0 MB]: 18573 frames
       Requested Block Size 16.0 MB
       Peak Block count 2
-      Peak Allocated memory 27.4 MB
+      Peak Allocated memory 22.7 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18576 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 21.7 MB
+      Peak Allocated memory 24.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -252,15 +252,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18575 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]: 18766 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18576 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -270,15 +270,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 198 frames, [1.0 MB-2.0 MB]: 18568 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 66 frames, [1.0 MB-2.0 MB]: 18510 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]: 18765 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18575 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
@@ -288,27 +288,27 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.5 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18766 frames
+      Peak usage frame count: [0-1.0 KB]: 18576 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]: 18766 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18576 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]: 18766 frames
+  Peak usage frame count: [16.0 KB-32.0 KB]: 18576 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
-  Peak Allocated memory 29.0 KB
+  Peak Allocated memory 29.2 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":1732216563188,"processId":13461,"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":1732221023335,"processId":31934,"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

@@ -2,189 +2,189 @@
     "name": "root",
     "gauges": {
         "Pyramids.Policy.Entropy.mean": {
-            "value": 0.3288368880748749,
-            "min": 0.3288368880748749,
-            "max": 0.6374443173408508,
-            "count": 33
+            "value": 0.22818312048912048,
+            "min": 0.2039005309343338,
+            "max": 0.34843266010284424,
+            "count": 99
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 10007.1640625,
-            "min": 10007.1640625,
-            "max": 19357.908203125,
-            "count": 33
+            "value": 2336.59521484375,
+            "min": 2022.59765625,
+            "max": 3625.49755859375,
+            "count": 99
         },
         "Pyramids.Step.mean": {
-            "value": 1979997.0,
-            "min": 1019958.0,
-            "max": 1979997.0,
-            "count": 33
+            "value": 2999881.0,
+            "min": 2019931.0,
+            "max": 2999881.0,
+            "count": 99
         },
         "Pyramids.Step.sum": {
-            "value": 1979997.0,
-            "min": 1019958.0,
-            "max": 1979997.0,
-            "count": 33
+            "value": 2999881.0,
+            "min": 2019931.0,
+            "max": 2999881.0,
+            "count": 99
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.3879289925098419,
-            "min": 0.022524673491716385,
-            "max": 0.49204227328300476,
-            "count": 33
+            "value": 0.5736708641052246,
+            "min": 0.3378733694553375,
+            "max": 0.7486498355865479,
+            "count": 99
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 105.90461730957031,
-            "min": 3.6715216636657715,
-            "max": 132.85140991210938,
-            "count": 33
+            "value": 55.64607238769531,
+            "min": 29.73285675048828,
+            "max": 72.61903381347656,
+            "count": 99
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": 0.025791283696889877,
-            "min": -0.005343945696949959,
-            "max": 0.03500159829854965,
-            "count": 33
+            "value": 0.014570897445082664,
+            "min": -0.03944053500890732,
+            "max": 0.05313658341765404,
+            "count": 99
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": 7.041020393371582,
-            "min": -1.400113821029663,
-            "max": 9.520434379577637,
-            "count": 33
+            "value": 1.413377046585083,
+            "min": -3.5102076530456543,
+            "max": 4.8354291915893555,
+            "count": 99
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 333.6388888888889,
+            "min": 236.26829268292684,
+            "max": 528.5416666666666,
+            "count": 99
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 12011.0,
+            "min": 6701.0,
+            "max": 12969.0,
+            "count": 99
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5552110910001729,
+            "min": 0.9713416422406832,
+            "max": 1.7637316911685756,
+            "count": 99
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 55.98759927600622,
+            "min": 18.456599667668343,
+            "max": 77.4339993596077,
+            "count": 99
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5552110910001729,
+            "min": 0.9713416422406832,
+            "max": 1.7637316911685756,
+            "count": 99
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 55.98759927600622,
+            "min": 18.456599667668343,
+            "max": 77.4339993596077,
+            "count": 99
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.012661191034668364,
+            "min": 0.010234315305327375,
+            "max": 0.02412275473458673,
+            "count": 99
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 0.4558028772480611,
+            "min": 0.3069634706625948,
+            "max": 0.6234519142890349,
+            "count": 99
         },
         "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06406410573509955,
-            "min": 0.06406410573509955,
-            "max": 0.07185494447238182,
-            "count": 33
+            "value": 0.07239385832023497,
+            "min": 0.06083606162962193,
+            "max": 0.08046303343629309,
+            "count": 99
         },
         "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9609615860264932,
-            "min": 0.5398511573303993,
-            "max": 1.0491777876433095,
-            "count": 33
+            "value": 0.2895754332809399,
+            "min": 0.24499540900190672,
+            "max": 0.38217773906174385,
+            "count": 99
         },
         "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.01642818447567954,
-            "min": 0.0045277437953204925,
-            "max": 0.01642818447567954,
-            "count": 33
+            "value": 0.019561920593938947,
+            "min": 0.009507199352568326,
+            "max": 0.019673819832193355,
+            "count": 99
         },
         "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.2464227671351931,
-            "min": 0.04714187418616633,
-            "max": 0.2464227671351931,
-            "count": 33
+            "value": 0.07824768237575579,
+            "min": 0.04753599676284163,
+            "max": 0.09836909916096677,
+            "count": 99
         },
         "Pyramids.Policy.LearningRate.mean": {
-            "value": 5.2679782440400025e-06,
-            "min": 5.2679782440400025e-06,
-            "max": 0.0001482286630904625,
-            "count": 33
+            "value": 4.81924839391669e-07,
+            "min": 4.81924839391669e-07,
+            "max": 9.843306718899998e-05,
+            "count": 99
         },
         "Pyramids.Policy.LearningRate.sum": {
-            "value": 7.901967366060004e-05,
-            "min": 7.901967366060004e-05,
-            "max": 0.0020250700249769,
-            "count": 33
+            "value": 1.927699357566676e-06,
+            "min": 1.927699357566676e-06,
+            "max": 0.00048737203754276666,
+            "count": 99
         },
         "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10175595999999999,
-            "min": 0.10175595999999999,
-            "max": 0.14940953750000002,
-            "count": 33
+            "value": 0.10016060833333333,
+            "min": 0.10016060833333333,
+            "max": 0.13281099999999998,
+            "count": 99
         },
         "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.5263394,
-            "min": 1.1952763000000002,
-            "max": 2.11113025,
-            "count": 33
+            "value": 0.4006424333333333,
+            "min": 0.4006424333333333,
+            "max": 0.6624572333333334,
+            "count": 99
         },
         "Pyramids.Policy.Beta.mean": {
-            "value": 0.00018542040400000006,
-            "min": 0.00018542040400000006,
-            "max": 0.00494601279625,
-            "count": 33
+            "value": 2.6044772500000078e-05,
+            "min": 2.6044772500000078e-05,
+            "max": 0.0032878189,
+            "count": 99
         },
         "Pyramids.Policy.Beta.sum": {
-            "value": 0.002781306060000001,
-            "min": 0.002781306060000001,
-            "max": 0.06757480769,
-            "count": 33
+            "value": 0.00010417909000000031,
+            "min": 0.00010417909000000031,
+            "max": 0.01627947761,
+            "count": 99
         },
         "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.004714569076895714,
-            "min": 0.004656789358705282,
-            "max": 0.010158630087971687,
-            "count": 33
+            "value": 0.0037975877057760954,
+            "min": 0.0034002165775746107,
+            "max": 0.004954335745424032,
+            "count": 99
         },
         "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.07071853429079056,
-            "min": 0.06519505381584167,
-            "max": 0.1343543529510498,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 424.28169014084506,
-            "min": 377.63513513513516,
-            "max": 853.5714285714286,
-            "count": 33
-        },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30124.0,
-            "min": 13971.0,
-            "max": 34643.0,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 1.4348365983492892,
-            "min": -0.054011474975517816,
-            "max": 1.5696026442448299,
-            "count": 33
-        },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 101.87339848279953,
-            "min": -1.8904016241431236,
-            "max": 117.72019831836224,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 1.4348365983492892,
-            "min": -0.054011474975517816,
-            "max": 1.5696026442448299,
-            "count": 33
-        },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 101.87339848279953,
-            "min": -1.8904016241431236,
-            "max": 117.72019831836224,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.02140662624151446,
-            "min": 0.019622120888851822,
-            "max": 0.08475303877743759,
-            "count": 33
-        },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 1.5198704631475266,
-            "min": 1.4520369457750348,
-            "max": 3.013041902362602,
-            "count": 33
+            "value": 0.015190350823104382,
+            "min": 0.014114302583038807,
+            "max": 0.024441909044981003,
+            "count": 99
         },
         "Pyramids.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 99
         },
         "Pyramids.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 33
+            "count": 99
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1732214209",
+        "start_time_seconds": "1732218521",
         "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=PyramidsTraining --no-graphics --resume",
         "mlagents_version": "1.2.0.dev0",
@@ -192,59 +192,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.5.1+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1732216563"
+        "end_time_seconds": "1732221023"
     },
-    "total": 2353.9807636950004,
+    "total": 2502.2013380550006,
     "count": 1,
-    "self": 0.47639820800031885,
+    "self": 1.03047069600143,
     "children": {
         "run_training.setup": {
-            "total": 0.05796810199990432,
+            "total": 0.05815928999982134,
             "count": 1,
-            "self": 0.05796810199990432
+            "self": 0.05815928999982134
         },
         "TrainerController.start_learning": {
-            "total": 2353.446397385,
+            "total": 2501.1127080689994,
             "count": 1,
-            "self": 1.526080958845796,
+            "self": 1.504617217188752,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.201755490999858,
+                    "total": 2.2194132609993176,
                     "count": 1,
-                    "self": 2.201755490999858
+                    "self": 2.2194132609993176
                 },
                 "TrainerController.advance": {
-                    "total": 2349.6323508541545,
-                    "count": 64052,
-                    "self": 1.5457315301337076,
+                    "total": 2497.2515567588116,
+                    "count": 64279,
+                    "self": 1.4900339255045765,
                     "children": {
                         "env_step": {
-                            "total": 1653.2551761230015,
-                            "count": 64052,
-                            "self": 1495.9177507449986,
+                            "total": 1801.3886824350748,
+                            "count": 64279,
+                            "self": 1646.2148054726613,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 156.4607022899918,
-                                    "count": 64052,
-                                    "self": 4.826967040053205,
+                                    "total": 154.29393197544505,
+                                    "count": 64279,
+                                    "self": 4.788805176271126,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 151.63373524993858,
-                                            "count": 62552,
-                                            "self": 151.63373524993858
+                                            "total": 149.50512679917392,
+                                            "count": 61919,
+                                            "self": 149.50512679917392
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.8767230880112038,
-                                    "count": 64052,
+                                    "total": 0.8799449869684395,
+                                    "count": 64279,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2347.9183412740263,
-                                            "count": 64052,
+                                            "total": 2495.1740079530737,
+                                            "count": 64279,
                                             "is_parallel": true,
-                                            "self": 974.4295465497976,
+                                            "self": 973.0587914039843,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0025034629998117452,
+                                                            "total": 0.002083455000501999,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007505519997721422,
+                                                            "self": 0.0006852699998489697,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001752911000039603,
+                                                                    "total": 0.0013981850006530294,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001752911000039603
+                                                                    "self": 0.0013981850006530294
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04789147600013166,
+                                                            "total": 0.07345133800026815,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006273240001064551,
+                                                            "self": 0.00077427400083252,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0004943559997627744,
+                                                                    "total": 0.0004704079992734478,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0004943559997627744
+                                                                    "self": 0.0004704079992734478
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.045079006000378286,
+                                                                    "total": 0.07047250300001906,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.045079006000378286
+                                                                    "self": 0.07047250300001906
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0016907899998841458,
+                                                                    "total": 0.0017341530001431238,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003641870002866199,
+                                                                    "self": 0.0003282769994257251,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001326602999597526,
+                                                                            "total": 0.0014058760007173987,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001326602999597526
+                                                                            "self": 0.0014058760007173987
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1373.4887947242287,
-                                                    "count": 64051,
+                                                    "total": 1522.1152165490894,
+                                                    "count": 64278,
                                                     "is_parallel": true,
-                                                    "self": 34.013932495060544,
+                                                    "self": 33.778216410913046,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 23.274413845092567,
-                                                            "count": 64051,
+                                                            "total": 22.929515763988093,
+                                                            "count": 64278,
                                                             "is_parallel": true,
-                                                            "self": 23.274413845092567
+                                                            "self": 22.929515763988093
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1216.0480809410578,
-                                                            "count": 64051,
+                                                            "total": 1365.5666301870242,
+                                                            "count": 64278,
                                                             "is_parallel": true,
-                                                            "self": 1216.0480809410578
+                                                            "self": 1365.5666301870242
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 100.15236744301774,
-                                                            "count": 64051,
+                                                            "total": 99.84085418716404,
+                                                            "count": 64278,
                                                             "is_parallel": true,
-                                                            "self": 20.97420131192439,
+                                                            "self": 20.807059344434492,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 79.17816613109335,
-                                                                    "count": 512408,
+                                                                    "total": 79.03379484272955,
+                                                                    "count": 514224,
                                                                     "is_parallel": true,
-                                                                    "self": 79.17816613109335
+                                                                    "self": 79.03379484272955
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 694.8314432010193,
-                            "count": 64052,
-                            "self": 3.041502776978632,
+                            "total": 694.3728403982323,
+                            "count": 64279,
+                            "self": 3.0610461271799068,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 136.84945755504305,
-                                    "count": 64052,
-                                    "self": 136.64514838304422,
+                                    "total": 141.26418005904907,
+                                    "count": 64279,
+                                    "self": 140.94498355004816,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.2043091719988297,
+                                            "total": 0.31919650900090346,
                                             "count": 2,
-                                            "self": 0.2043091719988297
+                                            "self": 0.31919650900090346
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 554.9404828689976,
-                                    "count": 470,
-                                    "self": 310.48992824498146,
+                                    "total": 550.0476142120033,
+                                    "count": 467,
+                                    "self": 306.21744876890534,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 244.45055462401615,
-                                            "count": 22734,
-                                            "self": 244.45055462401615
+                                            "total": 243.83016544309794,
+                                            "count": 22482,
+                                            "self": 243.83016544309794
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.0469993867445737e-06,
+                    "total": 1.197999154101126e-06,
                     "count": 1,
-                    "self": 1.0469993867445737e-06
+                    "self": 1.197999154101126e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.08620903400060342,
+                    "total": 0.13711963400055538,
                     "count": 1,
-                    "self": 0.0018989680011145538,
+                    "self": 0.003714976000992465,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.08431006599948887,
+                            "total": 0.13340465799956291,
                             "count": 1,
-                            "self": 0.08431006599948887
+                            "self": 0.13340465799956291
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 1000080,
-                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000080.onnx",
-                "reward": null,
-                "creation_time": 1732214112.7854717,
-                "auxillary_file_paths": [
-                    "results/PyramidsTraining/Pyramids/Pyramids-1000080.pt"
-                ]
-            },
             {
                 "steps": 1000080,
                 "file_path": "results/PyramidsTraining/Pyramids/Pyramids-1000080.onnx",
@@ -45,15 +36,51 @@
                 "auxillary_file_paths": [
                     "results/PyramidsTraining/Pyramids/Pyramids-2000205.pt"
                 ]
+            },
+            {
+                "steps": 2010391,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2010391.onnx",
+                "reward": 1.6227999806404114,
+                "creation_time": 1732218487.7648191,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-2010391.pt"
+                ]
+            },
+            {
+                "steps": 2499940,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2499940.onnx",
+                "reward": 1.7549999952316284,
+                "creation_time": 1732219745.3607726,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-2499940.pt"
+                ]
+            },
+            {
+                "steps": 2999881,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-2999881.onnx",
+                "reward": 1.36455554018418,
+                "creation_time": 1732221022.2000432,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-2999881.pt"
+                ]
+            },
+            {
+                "steps": 3000009,
+                "file_path": "results/PyramidsTraining/Pyramids/Pyramids-3000009.onnx",
+                "reward": 1.36455554018418,
+                "creation_time": 1732221022.3533678,
+                "auxillary_file_paths": [
+                    "results/PyramidsTraining/Pyramids/Pyramids-3000009.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000205,
+            "steps": 3000009,
             "file_path": "results/PyramidsTraining/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1732216562.7638965,
+            "reward": 1.36455554018418,
+            "creation_time": 1732221022.3533678,
             "auxillary_file_paths": [
-                "results/PyramidsTraining/Pyramids/Pyramids-2000205.pt"
+                "results/PyramidsTraining/Pyramids/Pyramids-3000009.pt"
             ]
         }
     },