train on additional 1m steps

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76ab4cc5c2454a034769b7600ad973c0af54d1ec46d918e0ab027c521bdbb3c5
+oid sha256:0fbcd8f78abb7d5c2070385f735355585353b163a32f132d5341ea6c89a5b9d4
 size 2273984

Huggy/Huggy-2199970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a4641cf414342d247d103850177a8429de99efd16f41af27e76bddd7c625ea
+size 2273984

Huggy/Huggy-2199970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd5e18bf2ba31c54b51a714a01da0e2eb3cd6236a6331606a3e03aaf3e6c508
+size 13509473

Huggy/Huggy-2399874.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86e349b6053f96db214adb4e04687560a483a3c1291ac981a0b868eddeb6bc0
+size 2273984

Huggy/Huggy-2399874.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3436cb93c88c3614865af55899b15d2c254d83bce1f88b8389af4a85d1310f1
+size 13509473

Huggy/Huggy-2599974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110e2d32f5d0cbf3a053d03d5abd74d0c3cb45c3cc7fe5ba5869bd5ff2722096
+size 2273984

Huggy/Huggy-2599974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18838d0540988f314c4d0546db861d75e8e7009a28811702cfbe641587ccc515
+size 13509473

Huggy/Huggy-2799921.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c380a6c5b7462ce520577edeb1aa0171e2528a05bbe2305d2f443730a5631ef
+size 2273984

Huggy/Huggy-2799921.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d957ae0319ba90c9a0d47dac549bcbacbc749aac7187a697958ed32c00f730c
+size 13509473

Huggy/Huggy-2999908.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d51d08e6ebb9dc3f536547658892366445716863d9f46b07e18cdbfb199cd2
+size 2273984

Huggy/Huggy-2999908.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7d5518395802863bc468f2cce6eed404b5c7be37331ce7c1b4a1b3cca93dc8
+size 13509473

Huggy/Huggy-3000012.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fbcd8f78abb7d5c2070385f735355585353b163a32f132d5341ea6c89a5b9d4
+size 2273984

Huggy/Huggy-3000012.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d7bb5b669f3c77ef516066765556b6350aa3be87597284712e581baf7bca0b
+size 13509473

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bd03afe4f0777dd184f88dee622b7680a6926b73a6ebadcf97e94049c79532
+oid sha256:c371157dfc1ba4c7028454ac4e81f03d27d3f733c76d9df46cfe0fe33f3be406
 size 13509218

Huggy/events.out.tfevents.1707229530.20a3ae5a77fc.19980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d5b623d0b78c09f067645e4fc464ab01a72545d3a7ff8a2de0c53e9ed17d4fe
+size 1121

Huggy/events.out.tfevents.1707229684.20a3ae5a77fc.20673.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca15258ea74ef91fb5ad88ac8103fd5ef958c122b4e14e9c59971959afb8cdd0
+size 176578

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "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": "Huggy", "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

@@ -38,7 +38,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 15
     even_checkpoints: false
-    max_steps: 2000000
+    max_steps: 3000000
     time_horizon: 1000
     summary_freq: 50000
     threaded: false
@@ -69,7 +69,7 @@ checkpoint_settings:
   run_id: Huggy
   initialize_from: null
   load_model: false
-  resume: false
+  resume: true
   force: false
   train_model: false
   inference: false

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ 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  0.088 seconds
+- Completed reload, in  0.101 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +75,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - 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: 0.773317 ms
+UnloadTime: 0.783364 ms
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26755 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 13418 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -93,7 +90,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 152 B
+      Peak Allocated Bytes 176 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,22 +198,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 212
+  Peak main deferred allocation count 326
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26756 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 13419 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 23.2 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26756 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 13419 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.6 MB
+      Peak Allocated memory 2.5 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -245,13 +242,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26755 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 13418 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26756 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 13419 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26755 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 13418 frames, [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 24.9 MB
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 26755 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 13418 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -281,13 +278,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26756 frames
+      Peak usage frame count: [0-1.0 KB]: 13419 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: [4.0 KB-8.0 KB]: 26756 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 13419 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,213 +2,213 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.40479576587677,
-            "min": 1.40479576587677,
-            "max": 1.4262832403182983,
-            "count": 40
+            "value": 1.4002948999404907,
+            "min": 1.400290846824646,
+            "max": 1.4044567346572876,
+            "count": 20
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 70746.921875,
-            "min": 68906.0859375,
-            "max": 77985.328125,
-            "count": 40
+            "value": 70707.890625,
+            "min": 68126.109375,
+            "max": 71574.140625,
+            "count": 20
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 76.35085007727976,
-            "min": 74.21385542168674,
-            "max": 386.5615384615385,
-            "count": 40
+            "value": 92.73170731707317,
+            "min": 66.15725806451613,
+            "max": 92.73170731707317,
+            "count": 20
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49399.0,
-            "min": 49278.0,
-            "max": 50253.0,
-            "count": 40
+            "value": 49426.0,
+            "min": 49221.0,
+            "max": 49556.0,
+            "count": 20
         },
         "Huggy.Step.mean": {
-            "value": 1999987.0,
-            "min": 49991.0,
-            "max": 1999987.0,
-            "count": 40
+            "value": 2999908.0,
+            "min": 2049981.0,
+            "max": 2999908.0,
+            "count": 20
         },
         "Huggy.Step.sum": {
-            "value": 1999987.0,
-            "min": 49991.0,
-            "max": 1999987.0,
-            "count": 40
+            "value": 2999908.0,
+            "min": 2049981.0,
+            "max": 2999908.0,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.4954729080200195,
-            "min": 0.10935484617948532,
-            "max": 2.5171620845794678,
-            "count": 40
+            "value": 2.4432694911956787,
+            "min": 2.442089557647705,
+            "max": 2.5468037128448486,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1614.571044921875,
-            "min": 14.106775283813477,
-            "max": 1650.9215087890625,
-            "count": 40
+            "value": 1302.2626953125,
+            "min": 1302.2626953125,
+            "max": 1863.03515625,
+            "count": 20
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.9151884355169178,
-            "min": 1.7759710487931273,
-            "max": 4.0382681907269,
-            "count": 40
+            "value": 3.7131219303853964,
+            "min": 3.7131219303853964,
+            "max": 4.026137485445201,
+            "count": 20
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 2533.1269177794456,
-            "min": 229.10026529431343,
-            "max": 2586.368226826191,
-            "count": 40
+            "value": 1979.0939888954163,
+            "min": 1979.0939888954163,
+            "max": 2931.028089404106,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.9151884355169178,
-            "min": 1.7759710487931273,
-            "max": 4.0382681907269,
-            "count": 40
+            "value": 3.7131219303853964,
+            "min": 3.7131219303853964,
+            "max": 4.026137485445201,
+            "count": 20
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 2533.1269177794456,
-            "min": 229.10026529431343,
-            "max": 2586.368226826191,
-            "count": 40
+            "value": 1979.0939888954163,
+            "min": 1979.0939888954163,
+            "max": 2931.028089404106,
+            "count": 20
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.019103528304711088,
-            "min": 0.014227674743203049,
-            "max": 0.020454438457575937,
-            "count": 40
+            "value": 0.016497817036967413,
+            "min": 0.014403317138850171,
+            "max": 0.021526213961381775,
+            "count": 20
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.05731058491413326,
-            "min": 0.028455349486406097,
-            "max": 0.057827948908864835,
-            "count": 40
+            "value": 0.032995634073934826,
+            "min": 0.03035465927775173,
+            "max": 0.056156814580026554,
+            "count": 20
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.05863657374348905,
-            "min": 0.02132847082490722,
-            "max": 0.0604518906523784,
-            "count": 40
+            "value": 0.047286525989572205,
+            "min": 0.047286525989572205,
+            "max": 0.0675045739238461,
+            "count": 20
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.17590972123046716,
-            "min": 0.04265694164981444,
-            "max": 0.1813556719571352,
-            "count": 40
+            "value": 0.09457305197914441,
+            "min": 0.09457305197914441,
+            "max": 0.18123736369113128,
+            "count": 20
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.6815987728333375e-06,
-            "min": 3.6815987728333375e-06,
-            "max": 0.0002953593765468749,
-            "count": 40
+            "value": 2.3148492284166755e-06,
+            "min": 2.3148492284166755e-06,
+            "max": 9.691496769503332e-05,
+            "count": 20
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 1.1044796318500013e-05,
-            "min": 1.1044796318500013e-05,
-            "max": 0.0008440443186519,
-            "count": 40
+            "value": 4.629698456833351e-06,
+            "min": 4.629698456833351e-06,
+            "max": 0.00026304131231963336,
+            "count": 20
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10122716666666669,
-            "min": 0.10122716666666669,
-            "max": 0.19845312500000006,
-            "count": 40
+            "value": 0.10077158333333334,
+            "min": 0.10077158333333334,
+            "max": 0.1323049666666667,
+            "count": 20
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30368150000000005,
-            "min": 0.2076262,
-            "max": 0.5813480999999999,
-            "count": 40
+            "value": 0.2015431666666667,
+            "min": 0.2015431666666667,
+            "max": 0.3876803666666667,
+            "count": 20
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 7.123561666666675e-05,
-            "min": 7.123561666666675e-05,
-            "max": 0.004922810937499999,
-            "count": 40
+            "value": 4.850200833333351e-05,
+            "min": 4.850200833333351e-05,
+            "max": 0.0016220178366666666,
+            "count": 20
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00021370685000000024,
-            "min": 0.00021370685000000024,
-            "max": 0.014069270190000002,
-            "count": 40
+            "value": 9.700401666666702e-05,
+            "min": 9.700401666666702e-05,
+            "max": 0.004405250296666668,
+            "count": 20
         },
         "Huggy.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         },
         "Huggy.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 20
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1707226407",
+        "start_time_seconds": "1707229684",
         "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --resume",
         "mlagents_version": "1.1.0.dev0",
         "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "2.2.0+cu121",
         "numpy_version": "1.23.5",
-        "end_time_seconds": "1707228817"
+        "end_time_seconds": "1707230903"
     },
-    "total": 2409.440081134,
+    "total": 1219.2884672870005,
     "count": 1,
-    "self": 0.44169744000009814,
+    "self": 0.4370836470006907,
     "children": {
         "run_training.setup": {
-            "total": 0.04923977999987983,
+            "total": 0.04692796699964674,
             "count": 1,
-            "self": 0.04923977999987983
+            "self": 0.04692796699964674
         },
         "TrainerController.start_learning": {
-            "total": 2408.949143914,
+            "total": 1218.8044556730001,
             "count": 1,
-            "self": 4.509431323028366,
+            "self": 2.343180128024869,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.9892884610001147,
+                    "total": 2.1479978630004553,
                     "count": 1,
-                    "self": 2.9892884610001147
+                    "self": 2.1479978630004553
                 },
                 "TrainerController.advance": {
-                    "total": 2401.323403468972,
-                    "count": 233222,
-                    "self": 4.9041543729199475,
+                    "total": 1214.1848600489748,
+                    "count": 118128,
+                    "self": 2.452056089875441,
                     "children": {
                         "env_step": {
-                            "total": 1939.5104788280173,
-                            "count": 233222,
-                            "self": 1609.9971716006812,
+                            "total": 974.6812306079783,
+                            "count": 118128,
+                            "self": 807.4357161978896,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 326.6790022380692,
-                                    "count": 233222,
-                                    "self": 16.749791363120494,
+                                    "total": 165.77706546212357,
+                                    "count": 118128,
+                                    "self": 8.387665497116359,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 309.9292108749487,
-                                            "count": 222963,
-                                            "self": 309.9292108749487
+                                            "total": 157.38939996500721,
+                                            "count": 111823,
+                                            "self": 157.38939996500721
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.8343049892669114,
-                                    "count": 233222,
+                                    "total": 1.4684489479650438,
+                                    "count": 118128,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2401.659049063007,
-                                            "count": 233222,
+                                            "total": 1214.8518558820324,
+                                            "count": 118128,
                                             "is_parallel": true,
-                                            "self": 1088.6713370230154,
+                                            "self": 556.5244112889222,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -217,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009009340001284727,
+                                                            "total": 0.0011551730003702687,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00025307400005658565,
+                                                            "self": 0.00035466300050757127,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.000647860000071887,
+                                                                    "total": 0.0008005099998626974,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000647860000071887
+                                                                    "self": 0.0008005099998626974
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.032897016000106305,
+                                                            "total": 0.02979850100018666,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00039493999975093175,
+                                                            "self": 0.0003212329993402818,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00025312900015705964,
+                                                                    "total": 0.00020562200006679632,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00025312900015705964
+                                                                    "self": 0.00020562200006679632
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.03144854800007124,
+                                                                    "total": 0.028506298000138486,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.03144854800007124
+                                                                    "self": 0.028506298000138486
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0008003990001270722,
+                                                                    "total": 0.0007653480006410973,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00020498000026236696,
+                                                                    "self": 0.00022463200002675876,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005954189998647053,
+                                                                            "total": 0.0005407160006143386,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005954189998647053
+                                                                            "self": 0.0005407160006143386
                                                                         }
                                                                     }
                                                                 }
@@ -267,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1312.9877120399915,
-                                                    "count": 233221,
+                                                    "total": 658.3274445931102,
+                                                    "count": 118127,
                                                     "is_parallel": true,
-                                                    "self": 41.25639111639907,
+                                                    "self": 20.83874480905888,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 85.96511211693633,
-                                                            "count": 233221,
+                                                            "total": 43.2128352530126,
+                                                            "count": 118127,
                                                             "is_parallel": true,
-                                                            "self": 85.96511211693633
+                                                            "self": 43.2128352530126
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1092.4745247058486,
-                                                            "count": 233221,
+                                                            "total": 547.4930454870992,
+                                                            "count": 118127,
                                                             "is_parallel": true,
-                                                            "self": 1092.4745247058486
+                                                            "self": 547.4930454870992
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 93.29168410080752,
-                                                            "count": 233221,
+                                                            "total": 46.782819043939526,
+                                                            "count": 118127,
                                                             "is_parallel": true,
-                                                            "self": 34.65772516784432,
+                                                            "self": 17.487023304808645,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 58.633958932963196,
-                                                                    "count": 466442,
+                                                                    "total": 29.29579573913088,
+                                                                    "count": 236254,
                                                                     "is_parallel": true,
-                                                                    "self": 58.633958932963196
+                                                                    "self": 29.29579573913088
                                                                 }
                                                             }
                                                         }
@@ -307,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 456.90877026803514,
-                            "count": 233222,
-                            "self": 6.625547788050881,
+                            "total": 237.05157335112108,
+                            "count": 118128,
+                            "self": 3.40058024413338,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 158.5469349989853,
-                                    "count": 233222,
-                                    "self": 157.33874496698422,
+                                    "total": 86.32439864298885,
+                                    "count": 118128,
+                                    "self": 85.67243265498837,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2081900320010845,
-                                            "count": 10,
-                                            "self": 1.2081900320010845
+                                            "total": 0.6519659880004838,
+                                            "count": 5,
+                                            "self": 0.6519659880004838
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 291.73628748099895,
-                                    "count": 97,
-                                    "self": 231.13104093599577,
+                                    "total": 147.32659446399884,
+                                    "count": 48,
+                                    "self": 116.61226426998746,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 60.60524654500318,
-                                            "count": 2910,
-                                            "self": 60.60524654500318
+                                            "total": 30.71433019401138,
+                                            "count": 1440,
+                                            "self": 30.71433019401138
                                         }
                                     }
                                 }
@@ -340,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.3639996723213699e-06,
+                    "total": 1.5639998309779912e-06,
                     "count": 1,
-                    "self": 1.3639996723213699e-06
+                    "self": 1.5639998309779912e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.12701929700006076,
+                    "total": 0.12841606900019542,
                     "count": 1,
-                    "self": 0.002057402000446018,
+                    "self": 0.0030520170003001112,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12496189499961474,
+                            "total": 0.1253640519998953,
                             "count": 1,
-                            "self": 0.12496189499961474
+                            "self": 0.1253640519998953
                         }
                     }
                 }

run_logs/training_status.json

@@ -1,33 +1,6 @@
 {
     "Huggy": {
         "checkpoints": [
-            {
-                "steps": 199955,
-                "file_path": "results/Huggy/Huggy/Huggy-199955.onnx",
-                "reward": 3.8129177585480707,
-                "creation_time": 1707226645.5971615,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199955.pt"
-                ]
-            },
-            {
-                "steps": 399953,
-                "file_path": "results/Huggy/Huggy/Huggy-399953.onnx",
-                "reward": 3.5436155513713232,
-                "creation_time": 1707226884.371544,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399953.pt"
-                ]
-            },
-            {
-                "steps": 599972,
-                "file_path": "results/Huggy/Huggy/Huggy-599972.onnx",
-                "reward": 4.225136029092889,
-                "creation_time": 1707227124.4800828,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599972.pt"
-                ]
-            },
             {
                 "steps": 799987,
                 "file_path": "results/Huggy/Huggy/Huggy-799987.onnx",
@@ -99,15 +72,78 @@
                 "auxillary_file_paths": [
                     "results/Huggy/Huggy/Huggy-2000079.pt"
                 ]
+            },
+            {
+                "steps": 2000079,
+                "file_path": "results/Huggy/Huggy/Huggy-2000079.onnx",
+                "reward": null,
+                "creation_time": 1707229532.083456,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2000079.pt"
+                ]
+            },
+            {
+                "steps": 2199970,
+                "file_path": "results/Huggy/Huggy/Huggy-2199970.onnx",
+                "reward": 3.867090335268995,
+                "creation_time": 1707229928.373752,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2199970.pt"
+                ]
+            },
+            {
+                "steps": 2399874,
+                "file_path": "results/Huggy/Huggy/Huggy-2399874.onnx",
+                "reward": 4.00003276743106,
+                "creation_time": 1707230173.364886,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2399874.pt"
+                ]
+            },
+            {
+                "steps": 2599974,
+                "file_path": "results/Huggy/Huggy/Huggy-2599974.onnx",
+                "reward": 4.05236953496933,
+                "creation_time": 1707230418.801743,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2599974.pt"
+                ]
+            },
+            {
+                "steps": 2799921,
+                "file_path": "results/Huggy/Huggy/Huggy-2799921.onnx",
+                "reward": 3.8115060528119407,
+                "creation_time": 1707230660.7077575,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2799921.pt"
+                ]
+            },
+            {
+                "steps": 2999908,
+                "file_path": "results/Huggy/Huggy/Huggy-2999908.onnx",
+                "reward": 3.62165554612875,
+                "creation_time": 1707230902.9507375,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2999908.pt"
+                ]
+            },
+            {
+                "steps": 3000012,
+                "file_path": "results/Huggy/Huggy/Huggy-3000012.onnx",
+                "reward": 3.630279859052087,
+                "creation_time": 1707230903.0828722,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-3000012.pt"
+                ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000079,
+            "steps": 3000012,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 4.344622765887867,
-            "creation_time": 1707228816.7219145,
+            "reward": 3.630279859052087,
+            "creation_time": 1707230903.0828722,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000079.pt"
+                "results/Huggy/Huggy/Huggy-3000012.pt"
             ]
         }
     },