Resume to 2M steps

Pyramids.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ca62f35fc5d7394234d7b8d27be41b6befe00a0c4c7f70f74f67c1d791fd57c
+oid sha256:f0e98a47e0e27961cee874301327b23b6fb30fe77b0eb66fe784922eaf0ae7cc
 size 1420238

Pyramids/Pyramids-1499907.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa06a8da7b6443d3eebb2592bd49260e403340c618b2b8a064125b13f137cd55
+size 1420238

Pyramids/Pyramids-1499907.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b5e6865bf6ee3dca077e97a4780b24b8150862809ec601608c1b96054594936
+size 8656079

Pyramids/Pyramids-1999987.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e98a47e0e27961cee874301327b23b6fb30fe77b0eb66fe784922eaf0ae7cc
+size 1420238

Pyramids/Pyramids-1999987.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ce9b444377d4d1aefd6f2613404ccb9cce9357a47c55f2debae3130373ee4d
+size 8656079

Pyramids/Pyramids-2000115.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e98a47e0e27961cee874301327b23b6fb30fe77b0eb66fe784922eaf0ae7cc
+size 1420238

Pyramids/Pyramids-2000115.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:785f3b615a1fb73c98c047f5aca86572d615775cf182f37fd65628418029df35
+size 8656079

Pyramids/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba65a33e89ebb3ac70cd832b8c88d22186bb9e3c3c45ce39db92957a1e2f2cf3
+oid sha256:ef51932da7f42a3dba535a80fe78c42f618e932ca54f784c9a7db700dcf25714
 size 8655605

Pyramids/events.out.tfevents.1793254485.ctr-smc-s23-44.adc.amd.com.3833066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dd1d8881e5dc047baf8e91a9013a7cb7f87d1e0740e62db665e44861c763556
+size 333718

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": "Pyramids1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 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": "Pyramids1", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": "cuda"}, "debug": false}

configuration.yaml

@@ -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: Pyramids1
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -1,7 +1,7 @@
 Mono path[0] = '/home/AMD/absheikh/rl-experiments/mlagents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
 Mono config path = '/home/AMD/absheikh/rl-experiments/mlagents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
 Found 2 interfaces on host : 0) 10.7.36.48 1) 172.17.0.1
-Multi-casting "[IP] 10.7.36.48 [Port] 55359 [Flags] 2 [Guid] 2652321264 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.7.36.48) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Multi-casting "[IP] 10.7.36.48 [Port] 55443 [Flags] 2 [Guid] 1097426701 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,10.7.36.48) [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:2721:(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  0.225 seconds
+- Completed reload, in  0.218 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: 0.771645 ms
+UnloadTime: 0.806035 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 28 worker threads for Enlighten.
@@ -73,22 +73,22 @@ PlayerConnection::CleanupMemory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [16.0 KB-32.0 KB]: 7391 frames, [32.0 KB-64.0 KB]: 9684 frames, [64.0 KB-128.0 KB]: 1695 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [16.0 KB-32.0 KB]: 247 frames, [32.0 KB-64.0 KB]: 13643 frames, [64.0 KB-128.0 KB]: 4875 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 44]
+    [ALLOC_TEMP_Job.Worker 18]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 18]
+    [ALLOC_TEMP_Job.Worker 44]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 45]
+    [ALLOC_TEMP_Job.Worker 19]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -201,19 +201,19 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Profiler.Dispatcher]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 136 B
+      Peak Allocated Bytes 7.5 KB
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 3]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 3]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -246,7 +246,12 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 11]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0.8 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
       Initial Block Size 256.0 KB
@@ -273,9 +278,9 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 6]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.AsyncRead]
@@ -293,32 +298,32 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 16]
-      Initial Block Size 256.0 KB
-      Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 52]
+    [ALLOC_TEMP_Job.Worker 40]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 40]
+    [ALLOC_TEMP_Job.Worker 16]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 6]
+    [ALLOC_TEMP_Background Job.Worker 10]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 52]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 1]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 10]
+    [ALLOC_TEMP_Background Job.Worker 6]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -333,11 +338,6 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Job.Worker 20]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
@@ -353,17 +353,17 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 30]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 31]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 31]
+    [ALLOC_TEMP_Job.Worker 29]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -373,16 +373,11 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 29]
+    [ALLOC_TEMP_Job.Worker 30]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 15]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
-      Peak Allocated Bytes 0 B
-      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 7]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -393,7 +388,7 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 23]
+    [ALLOC_TEMP_Job.Worker 1]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -403,17 +398,22 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 24]
+    [ALLOC_TEMP_Job.Worker 33]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 1]
+    [ALLOC_TEMP_Job.Worker 24]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 33]
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 23]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
@@ -438,12 +438,12 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 4]
+    [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 0]
+    [ALLOC_TEMP_Background Job.Worker 4]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
@@ -456,7 +456,7 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_TEMP_Job.Worker 48]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
-      Peak Allocated Bytes 0 B
+      Peak Allocated Bytes 0.8 KB
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 28]
       Initial Block Size 256.0 KB
@@ -468,34 +468,34 @@ PlayerConnection::CleanupMemory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 19]
+    [ALLOC_TEMP_Job.Worker 45]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_MEMORYPROFILER]
-  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+  Peak usage frame count: [0.5 MB-1.0 MB]: 94 frames, [1.0 MB-2.0 MB]: 18672 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 12474
+  Peak main deferred allocation count 2345
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18770 frames
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18765 frames
       Requested Block Size 16.0 MB
-      Peak Block count 3
-      Peak Allocated memory 31.6 MB
+      Peak Block count 2
+      Peak Allocated memory 24.4 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 213 frames, [32.0 MB-64.0 MB]: 18558 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
       Requested Block Size 16.0 MB
-      Peak Block count 2
-      Peak Allocated memory 33.0 MB
+      Peak Block count 1
+      Peak Allocated memory 31.6 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -522,15 +522,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 18770 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 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]: 18771 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 67.7 KB
@@ -540,15 +540,15 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18472 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 108 frames, [1.0 MB-2.0 MB]: 18658 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]: 18770 frames, [4.0 MB-8.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18765 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
@@ -558,21 +558,21 @@ PlayerConnection::CleanupMemory Statistics:
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
-      Peak Allocated bytes 1.7 MB
+      Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 18771 frames
+      Peak usage frame count: [0-1.0 KB]: 18766 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]: 18771 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18766 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: [64.0 KB-128.0 KB]: 18771 frames
+  Peak usage frame count: [64.0 KB-128.0 KB]: 18766 frames
   Requested Block Size 16.0 MB
   Peak Block count 1
   Peak Allocated memory 72.8 KB
@@ -581,4 +581,4 @@ PlayerConnection::CleanupMemory Statistics:
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 396 B
-##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1793252498311,"processId":3803479,"allocatedMemory":2030825,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35972},{"Manager":46987},{"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":4211},{"DynamicArray":30868},{"HashMap":7680},{"Utility":23392},{"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":1793257088297,"processId":3833301,"allocatedMemory":2030181,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35972},{"Manager":46987},{"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":3567},{"DynamicArray":30868},{"HashMap":7680},{"Utility":23392},{"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": 0.6399558782577515,
-            "min": 0.6276199817657471,
-            "max": 1.3740746974945068,
+            "value": 0.30431222915649414,
+            "min": 0.2997888922691345,
+            "max": 0.6104104518890381,
             "count": 33
         },
         "Pyramids.Policy.Entropy.sum": {
-            "value": 19208.916015625,
-            "min": 18768.34765625,
-            "max": 41683.9296875,
+            "value": 9080.6767578125,
+            "min": 8960.0908203125,
+            "max": 16852.814453125,
             "count": 33
         },
         "Pyramids.Step.mean": {
-            "value": 989974.0,
-            "min": 29952.0,
-            "max": 989974.0,
+            "value": 1979898.0,
+            "min": 1019966.0,
+            "max": 1979898.0,
             "count": 33
         },
         "Pyramids.Step.sum": {
-            "value": 989974.0,
-            "min": 29952.0,
-            "max": 989974.0,
+            "value": 1979898.0,
+            "min": 1019966.0,
+            "max": 1979898.0,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 0.2209072709083557,
-            "min": -0.10663755238056183,
-            "max": 0.2209072709083557,
+            "value": 0.6447826623916626,
+            "min": 0.19637173414230347,
+            "max": 0.6562128663063049,
             "count": 33
         },
         "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 57.435890197753906,
-            "min": -25.699649810791016,
-            "max": 57.435890197753906,
+            "value": 184.4078369140625,
+            "min": 33.053504943847656,
+            "max": 190.95794677734375,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.mean": {
-            "value": -0.062623992562294,
-            "min": -0.062623992562294,
-            "max": 0.4005627930164337,
+            "value": 0.03329402953386307,
+            "min": -0.01989748328924179,
+            "max": 0.05321849510073662,
             "count": 33
         },
         "Pyramids.Policy.RndValueEstimate.sum": {
-            "value": -16.282238006591797,
-            "min": -16.282238006591797,
-            "max": 94.93338012695312,
+            "value": 9.522092819213867,
+            "min": -3.5995655059814453,
+            "max": 15.220489501953125,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.mean": {
-            "value": 0.06869540844594926,
-            "min": 0.06531820088291272,
-            "max": 0.07380205167592628,
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 285.9191919191919,
+            "min": 285.9191919191919,
+            "max": 680.25,
             "count": 33
         },
-        "Pyramids.Losses.PolicyLoss.sum": {
-            "value": 0.9617357182432896,
-            "min": 0.4698894082882372,
-            "max": 1.041185449578288,
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28306.0,
+            "min": 14965.0,
+            "max": 32524.0,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.mean": {
-            "value": 0.011012141503020498,
-            "min": 3.955989882839828e-05,
-            "max": 0.011012141503020498,
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.673664635028502,
+            "min": 0.7740999665111303,
+            "max": 1.7028437301826973,
             "count": 33
         },
-        "Pyramids.Losses.ValueLoss.sum": {
-            "value": 0.15416998104228696,
-            "min": 0.0005538385835975759,
-            "max": 0.15416998104228696,
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 165.6927988678217,
+            "min": 25.028599098324776,
+            "max": 175.2287978231907,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.mean": {
-            "value": 7.645383165857138e-06,
-            "min": 7.645383165857138e-06,
-            "max": 0.00029515063018788575,
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.673664635028502,
+            "min": 0.7740999665111303,
+            "max": 1.7028437301826973,
             "count": 33
         },
-        "Pyramids.Policy.LearningRate.sum": {
-            "value": 0.00010703536432199993,
-            "min": 0.00010703536432199993,
-            "max": 0.0032543456152182,
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 165.6927988678217,
+            "min": 25.028599098324776,
+            "max": 175.2287978231907,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.mean": {
-            "value": 0.10254842857142857,
-            "min": 0.10254842857142857,
-            "max": 0.19838354285714285,
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.02022557739418875,
+            "min": 0.02022557739418875,
+            "max": 0.07436142470065864,
             "count": 33
         },
-        "Pyramids.Policy.Epsilon.sum": {
-            "value": 1.435678,
-            "min": 1.3691136000000002,
-            "max": 2.3847818000000003,
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.002332162024686,
+            "min": 1.7513342385645956,
+            "max": 3.384325666411314,
             "count": 33
         },
-        "Pyramids.Policy.Beta.mean": {
-            "value": 0.00026458801428571417,
-            "min": 0.00026458801428571417,
-            "max": 0.00983851593142857,
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06973685804543839,
+            "min": 0.06500511600530617,
+            "max": 0.07271041034532355,
             "count": 33
         },
-        "Pyramids.Policy.Beta.sum": {
-            "value": 0.0037042321999999983,
-            "min": 0.0037042321999999983,
-            "max": 0.10849970182,
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9763160126361374,
+            "min": 0.63117190303966,
+            "max": 1.0808707605853367,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.mean": {
-            "value": 0.011835738085210323,
-            "min": 0.011544919572770596,
-            "max": 0.431034654378891,
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015258209392500466,
+            "min": 0.00792006672989893,
+            "max": 0.016616935935194813,
             "count": 33
         },
-        "Pyramids.Losses.RNDLoss.sum": {
-            "value": 0.16570033133029938,
-            "min": 0.1616288721561432,
-            "max": 3.017242670059204,
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21361493149500652,
+            "min": 0.07130846138695147,
+            "max": 0.2492540390279222,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.mean": {
-            "value": 571.2777777777778,
-            "min": 571.2777777777778,
-            "max": 999.0,
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 5.368051782110717e-06,
+            "min": 5.368051782110717e-06,
+            "max": 0.00014838731720424444,
             "count": 33
         },
-        "Pyramids.Environment.EpisodeLength.sum": {
-            "value": 30849.0,
-            "min": 15984.0,
-            "max": 33170.0,
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 7.515272494955003e-05,
+            "min": 7.515272494955003e-05,
+            "max": 0.0020259193246938,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.mean": {
-            "value": 0.9470814389211161,
-            "min": -1.0000000521540642,
-            "max": 0.9470814389211161,
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10178931785714287,
+            "min": 0.10178931785714287,
+            "max": 0.14946242222222225,
             "count": 33
         },
-        "Pyramids.Environment.CumulativeReward.sum": {
-            "value": 51.142397701740265,
-            "min": -32.000001668930054,
-            "max": 51.142397701740265,
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4250504500000003,
+            "min": 1.3451618000000003,
+            "max": 2.1336969,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.mean": {
-            "value": 0.9470814389211161,
-            "min": -1.0000000521540642,
-            "max": 0.9470814389211161,
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00018875285392857153,
+            "min": 0.00018875285392857153,
+            "max": 0.00495129598,
             "count": 33
         },
-        "Pyramids.Policy.ExtrinsicReward.sum": {
-            "value": 51.142397701740265,
-            "min": -32.000001668930054,
-            "max": 51.142397701740265,
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0026425399550000016,
+            "min": 0.0026425399550000016,
+            "max": 0.06760308938,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.mean": {
-            "value": 0.07030160584987176,
-            "min": 0.07030160584987176,
-            "max": 8.710205709561706,
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.006828136742115021,
+            "min": 0.0067711458541452885,
+            "max": 0.011052335612475872,
             "count": 33
         },
-        "Pyramids.Policy.RndReward.sum": {
-            "value": 3.796286715893075,
-            "min": 3.5264685546280816,
-            "max": 139.3632913529873,
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09559391438961029,
+            "min": 0.09479603916406631,
+            "max": 0.15666170418262482,
             "count": 33
         },
         "Pyramids.IsTraining.mean": {
@@ -184,67 +184,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1793250016",
+        "start_time_seconds": "1793254484",
         "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]",
-        "command_line_arguments": "/home/AMD/absheikh/rl-experiments/mlagents/.venv/bin/mlagents-learn PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --torch-device cuda",
+        "command_line_arguments": "/home/AMD/absheikh/rl-experiments/mlagents/.venv/bin/mlagents-learn PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --torch-device cuda --resume",
         "mlagents_version": "1.2.0.dev0",
         "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.8.0+rocm6.4",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1793252498"
+        "end_time_seconds": "1793257088"
     },
-    "total": 2482.0132517032325,
+    "total": 2604.074793931097,
     "count": 1,
-    "self": 0.4263673275709152,
+    "self": 0.47742811031639576,
     "children": {
         "run_training.setup": {
-            "total": 0.0777266826480627,
+            "total": 0.06643028743565083,
             "count": 1,
-            "self": 0.0777266826480627
+            "self": 0.06643028743565083
         },
         "TrainerController.start_learning": {
-            "total": 2481.5091576930135,
+            "total": 2603.5309355333447,
             "count": 1,
-            "self": 1.2732897568494081,
+            "self": 1.311373831704259,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.4282569885253906,
+                    "total": 3.610912276431918,
                     "count": 1,
-                    "self": 3.4282569885253906
+                    "self": 3.610912276431918
                 },
                 "TrainerController.advance": {
-                    "total": 2476.686512812972,
-                    "count": 63286,
-                    "self": 1.0978825725615025,
+                    "total": 2598.485748678446,
+                    "count": 64651,
+                    "self": 1.1605321392416954,
                     "children": {
                         "env_step": {
-                            "total": 1725.8196500055492,
-                            "count": 63286,
-                            "self": 1590.2291341722012,
+                            "total": 1845.6751594077796,
+                            "count": 64651,
+                            "self": 1708.3011282663792,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 134.8555871937424,
-                                    "count": 63286,
-                                    "self": 3.7733556870371103,
+                                    "total": 136.59161848947406,
+                                    "count": 64651,
+                                    "self": 3.7545344568789005,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 131.08223150670528,
-                                            "count": 62569,
-                                            "self": 131.08223150670528
+                                            "total": 132.83708403259516,
+                                            "count": 62552,
+                                            "self": 132.83708403259516
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.7349286396056414,
-                                    "count": 63286,
+                                    "total": 0.7824126519262791,
+                                    "count": 64651,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2477.9935811422765,
-                                            "count": 63286,
+                                            "total": 2599.9442357458174,
+                                            "count": 64651,
                                             "is_parallel": true,
-                                            "self": 1006.4654833823442,
+                                            "self": 1010.6800258178264,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -253,48 +253,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.002560686320066452,
+                                                            "total": 0.002752605825662613,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0007171481847763062,
+                                                            "self": 0.0008014291524887085,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0018435381352901459,
+                                                                    "total": 0.0019511766731739044,
                                                                     "count": 8,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0018435381352901459
+                                                                    "self": 0.0019511766731739044
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.037930289283394814,
+                                                            "total": 0.04453127086162567,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0008403658866882324,
+                                                            "self": 0.0008446723222732544,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0007114820182323456,
+                                                                    "total": 0.0004619453102350235,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007114820182323456
+                                                                    "self": 0.0004619453102350235
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03371799364686012,
+                                                                    "total": 0.04079294949769974,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03371799364686012
+                                                                    "self": 0.04079294949769974
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002660447731614113,
+                                                                    "total": 0.002431703731417656,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005457829684019089,
+                                                                    "self": 0.0005485024303197861,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.002114664763212204,
+                                                                            "total": 0.0018832013010978699,
                                                                             "count": 8,
                                                                             "is_parallel": true,
-                                                                            "self": 0.002114664763212204
+                                                                            "self": 0.0018832013010978699
                                                                         }
                                                                     }
                                                                 }
@@ -303,34 +303,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1471.5280977599323,
-                                                    "count": 63285,
+                                                    "total": 1589.264209927991,
+                                                    "count": 64650,
                                                     "is_parallel": true,
-                                                    "self": 49.39401368238032,
+                                                    "self": 49.84520725347102,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 35.69357052817941,
-                                                            "count": 63285,
+                                                            "total": 35.33832837827504,
+                                                            "count": 64650,
                                                             "is_parallel": true,
-                                                            "self": 35.69357052817941
+                                                            "self": 35.33832837827504
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1247.1319602131844,
-                                                            "count": 63285,
+                                                            "total": 1363.4573536273092,
+                                                            "count": 64650,
                                                             "is_parallel": true,
-                                                            "self": 1247.1319602131844
+                                                            "self": 1363.4573536273092
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 139.3085533361882,
-                                                            "count": 63285,
+                                                            "total": 140.62332066893578,
+                                                            "count": 64650,
                                                             "is_parallel": true,
-                                                            "self": 29.309324830770493,
+                                                            "self": 30.173125511035323,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 109.9992285054177,
-                                                                    "count": 506280,
+                                                                    "total": 110.45019515790045,
+                                                                    "count": 517200,
                                                                     "is_parallel": true,
-                                                                    "self": 109.9992285054177
+                                                                    "self": 110.45019515790045
                                                                 }
                                                             }
                                                         }
@@ -343,31 +343,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 749.7689802348614,
-                            "count": 63286,
-                            "self": 2.2939224150031805,
+                            "total": 751.6500571314245,
+                            "count": 64651,
+                            "self": 2.5493362862616777,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 96.45962408557534,
-                                    "count": 63286,
-                                    "self": 96.18843930028379,
+                                    "total": 101.81671574153006,
+                                    "count": 64651,
+                                    "self": 101.53502881899476,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 0.27118478529155254,
+                                            "total": 0.28168692253530025,
                                             "count": 2,
-                                            "self": 0.27118478529155254
+                                            "self": 0.28168692253530025
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 651.0154337342829,
-                                    "count": 438,
-                                    "self": 308.1185030620545,
+                                    "total": 647.2840051036328,
+                                    "count": 473,
+                                    "self": 306.71699279360473,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 342.89693067222834,
-                                            "count": 22833,
-                                            "self": 342.89693067222834
+                                            "total": 340.5670123100281,
+                                            "count": 22770,
+                                            "self": 340.5670123100281
                                         }
                                     }
                                 }
@@ -376,19 +376,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.67992639541626e-07,
+                    "total": 1.2423843145370483e-06,
                     "count": 1,
-                    "self": 8.67992639541626e-07
+                    "self": 1.2423843145370483e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12109726667404175,
+                    "total": 0.122899504378438,
                     "count": 1,
-                    "self": 0.01758323796093464,
+                    "self": 0.015762997791171074,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10351402871310711,
+                            "total": 0.10713650658726692,
                             "count": 1,
-                            "self": 0.10351402871310711
+                            "self": 0.10713650658726692
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,15 +1,6 @@
 {
     "Pyramids": {
         "checkpoints": [
-            {
-                "steps": 499935,
-                "file_path": "results/Pyramids1/Pyramids/Pyramids-499935.onnx",
-                "reward": null,
-                "creation_time": 1793251235.9137206,
-                "auxillary_file_paths": [
-                    "results/Pyramids1/Pyramids/Pyramids-499935.pt"
-                ]
-            },
             {
                 "steps": 999982,
                 "file_path": "results/Pyramids1/Pyramids/Pyramids-999982.onnx",
@@ -27,15 +18,42 @@
                 "auxillary_file_paths": [
                     "results/Pyramids1/Pyramids/Pyramids-1000110.pt"
                 ]
+            },
+            {
+                "steps": 1499907,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-1499907.onnx",
+                "reward": 1.784000001847744,
+                "creation_time": 1793255771.6156728,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-1499907.pt"
+                ]
+            },
+            {
+                "steps": 1999987,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-1999987.onnx",
+                "reward": 1.7759999781847,
+                "creation_time": 1793257087.7598166,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-1999987.pt"
+                ]
+            },
+            {
+                "steps": 2000115,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-2000115.onnx",
+                "reward": 1.7759999781847,
+                "creation_time": 1793257087.8738635,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-2000115.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1000110,
+            "steps": 2000115,
             "file_path": "results/Pyramids1/Pyramids.onnx",
-            "reward": null,
-            "creation_time": 1793252497.9252608,
+            "reward": 1.7759999781847,
+            "creation_time": 1793257087.8738635,
             "auxillary_file_paths": [
-                "results/Pyramids1/Pyramids/Pyramids-1000110.pt"
+                "results/Pyramids1/Pyramids/Pyramids-2000115.pt"
             ]
         }
     },