Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ece1ee7eb6f91dbcaef8b35390fec320d80c4044ff06f847c54086708038726
+oid sha256:3171982d07bb7b80125dbcb94cb89d6825cb7fd5772dfdd681f5df5afbb84a4a
 size 2271327

Huggy/{Huggy-48977.onnx → Huggy-199704.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ece1ee7eb6f91dbcaef8b35390fec320d80c4044ff06f847c54086708038726
+oid sha256:703c2e25bee935b2cf13ca32a8362f516a7ca55102d7889b896dd74548e6b8e0
 size 2271327

Huggy/{Huggy-48977.pt → Huggy-199704.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707c8d255d475586a2d1f13eed314fa6db26f02aed6fdb57290b84b16d171e1e
+oid sha256:5ebc10cba6d866141252d5a3f2c57a169c279fdfe79da3874d103fa8bedfbd83
 size 13503717

Huggy/Huggy-399436.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb2bc3b86bdadcb1f65d7560dfe78384f281612452b98215d52737e6b76b717
+size 2271327

Huggy/Huggy-399436.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8af5a2a6b24607933c31a35a7cc50ed33d05afdfacf807293cc16ad782cada4c
+size 13503717

Huggy/Huggy-599365.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181739a4d8bbf934e8bcf02a4565e4cefcff43c4e408b8ab0e91a9d2ec768c12
+size 2271327

Huggy/Huggy-599365.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c42b09d35e8036b38478f10de73f59af054fdcf42250d2a0ae13cce8697f074b
+size 13503717

Huggy/Huggy-639115.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3171982d07bb7b80125dbcb94cb89d6825cb7fd5772dfdd681f5df5afbb84a4a
+size 2271327

Huggy/Huggy-639115.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2dc37e274a584cf597aaa420338c8bca7e58f9fe31ff53d5a146ac7bac4feee
+size 13503717

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:707c8d255d475586a2d1f13eed314fa6db26f02aed6fdb57290b84b16d171e1e
+oid sha256:d2dc37e274a584cf597aaa420338c8bca7e58f9fe31ff53d5a146ac7bac4feee
 size 13503717

Huggy/{events.out.tfevents.1679321129.376f999cc1e3.3047.0 → events.out.tfevents.1679469957.deb6adb046ef.3186.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7c8b8a9a90d99db398838cf6d00166af7dfea14a443e394175cd954d107c1a
-size 1073
+oid sha256:607f70c979545477416e7f3e9b77702f71aa66740e1a31c9c6167c274b3739ec
+size 98194

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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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": 1024, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 80, "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, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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}

configuration.yaml

@@ -3,13 +3,13 @@ behaviors:
   Huggy:
     trainer_type: ppo
     hyperparameters:
-      batch_size: 2048
+      batch_size: 1024
       buffer_size: 20480
       learning_rate: 0.0003
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
-      num_epoch: 3
+      num_epoch: 80
       shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear

run_logs/Player-0.log

@@ -34,7 +34,7 @@ ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.088 seconds
+- Completed reload, in  0.082 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 +78,14 @@ 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: 0.876917 ms
+UnloadTime: 0.762781 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]: 722 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 8624 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 +93,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 144 B
+      Peak Allocated Bytes 184 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,22 +201,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 153
+  Peak main deferred allocation count 251
     [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]: 723 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8625 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 22.1 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 7 frames, [2.0 MB-4.0 MB]: 716 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 8625 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.3 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 +245,13 @@ 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]: 722 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8624 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]: 723 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 8625 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +263,13 @@ 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]: 722 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 8624 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]: 722 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 8624 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 +281,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 723 frames
+      Peak usage frame count: [0-1.0 KB]: 8625 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]: 723 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 8625 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -1,8 +1,154 @@
 {
     "name": "root",
+    "gauges": {
+        "Huggy.Policy.Entropy.mean": {
+            "value": -0.9997519254684448,
+            "min": -0.9997519254684448,
+            "max": 1.3444199562072754,
+            "count": 12
+        },
+        "Huggy.Policy.Entropy.sum": {
+            "value": -51449.234375,
+            "min": -51449.234375,
+            "max": 74374.65625,
+            "count": 12
+        },
+        "Huggy.Environment.EpisodeLength.mean": {
+            "value": 736.4776119402985,
+            "min": 291.5813953488372,
+            "max": 749.0,
+            "count": 12
+        },
+        "Huggy.Environment.EpisodeLength.sum": {
+            "value": 49344.0,
+            "min": 49344.0,
+            "max": 50434.0,
+            "count": 12
+        },
+        "Huggy.Step.mean": {
+            "value": 599365.0,
+            "min": 49816.0,
+            "max": 599365.0,
+            "count": 12
+        },
+        "Huggy.Step.sum": {
+            "value": 599365.0,
+            "min": 49816.0,
+            "max": 599365.0,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.03113461285829544,
+            "min": -0.03113461285829544,
+            "max": 0.9373863935470581,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -2.0860190391540527,
+            "min": -2.0860190391540527,
+            "max": 142.94837951660156,
+            "count": 12
+        },
+        "Huggy.Environment.CumulativeReward.mean": {
+            "value": -1.8258129038583877,
+            "min": -2.280529317446053,
+            "max": 2.8464112139718476,
+            "count": 12
+        },
+        "Huggy.Environment.CumulativeReward.sum": {
+            "value": -122.32946455851197,
+            "min": -155.0759935863316,
+            "max": 489.5827288031578,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicReward.mean": {
+            "value": -1.8258129038583877,
+            "min": -2.280529317446053,
+            "max": 2.8464112139718476,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicReward.sum": {
+            "value": -122.32946455851197,
+            "min": -155.0759935863316,
+            "max": 489.5827288031578,
+            "count": 12
+        },
+        "Huggy.Losses.PolicyLoss.mean": {
+            "value": 0.024143845412327777,
+            "min": 0.024143845412327777,
+            "max": 0.22492867085151375,
+            "count": 12
+        },
+        "Huggy.Losses.PolicyLoss.sum": {
+            "value": 0.04828769082465555,
+            "min": 0.04828769082465555,
+            "max": 0.4871628791210242,
+            "count": 12
+        },
+        "Huggy.Losses.ValueLoss.mean": {
+            "value": 0.00010986422367011528,
+            "min": 0.00010299552992506733,
+            "max": 0.010556814962110365,
+            "count": 12
+        },
+        "Huggy.Losses.ValueLoss.sum": {
+            "value": 0.00021972844734023057,
+            "min": 0.00020599105985013465,
+            "max": 0.02111362992422073,
+            "count": 12
+        },
+        "Huggy.Policy.LearningRate.mean": {
+            "value": 0.00021428867857044994,
+            "min": 0.00021428867857044994,
+            "max": 0.000295372576542475,
+            "count": 12
+        },
+        "Huggy.Policy.LearningRate.sum": {
+            "value": 0.0004285773571408999,
+            "min": 0.0004285773571408999,
+            "max": 0.0008440629186457,
+            "count": 12
+        },
+        "Huggy.Policy.Epsilon.mean": {
+            "value": 0.17142954999999999,
+            "min": 0.17142954999999999,
+            "max": 0.198457525,
+            "count": 12
+        },
+        "Huggy.Policy.Epsilon.sum": {
+            "value": 0.34285909999999997,
+            "min": 0.34285909999999997,
+            "max": 0.5813543000000001,
+            "count": 12
+        },
+        "Huggy.Policy.Beta.mean": {
+            "value": 0.003574334545000001,
+            "min": 0.003574334545000001,
+            "max": 0.0049230304975,
+            "count": 12
+        },
+        "Huggy.Policy.Beta.sum": {
+            "value": 0.007148669090000002,
+            "min": 0.007148669090000002,
+            "max": 0.01406957957,
+            "count": 12
+        },
+        "Huggy.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        },
+        "Huggy.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1679321123",
+        "start_time_seconds": "1679469951",
         "python_version": "3.9.16 (main, Dec  7 2022, 01:11:51) \n[GCC 9.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
         "mlagents_version": "0.31.0.dev0",
@@ -10,59 +156,59 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.11.0+cu102",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1679321194"
+        "end_time_seconds": "1679473560"
     },
-    "total": 71.24449333500002,
+    "total": 3609.1329525349997,
     "count": 1,
-    "self": 0.005160171000056835,
+    "self": 0.5558727650000037,
     "children": {
         "run_training.setup": {
-            "total": 0.11752343799992104,
+            "total": 0.1907406360001005,
             "count": 1,
-            "self": 0.11752343799992104
+            "self": 0.1907406360001005
         },
         "TrainerController.start_learning": {
-            "total": 71.12180972600004,
+            "total": 3608.3863391339996,
             "count": 1,
-            "self": 0.11807807900277112,
+            "self": 1.276497031926283,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 8.950330699999995,
+                    "total": 8.60012459799998,
                     "count": 1,
-                    "self": 8.950330699999995
+                    "self": 8.60012459799998
                 },
                 "TrainerController.advance": {
-                    "total": 61.668267910997315,
-                    "count": 6089,
-                    "self": 0.13235401698989335,
+                    "total": 3598.2700294030733,
+                    "count": 72573,
+                    "self": 1.4732234929861079,
                     "children": {
                         "env_step": {
-                            "total": 50.77910207900368,
-                            "count": 6089,
-                            "self": 42.52928674800455,
+                            "total": 607.735694285022,
+                            "count": 72573,
+                            "self": 510.3403054160889,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 8.176359801997478,
-                                    "count": 6089,
-                                    "self": 0.5993841869977814,
+                                    "total": 96.4992278729726,
+                                    "count": 72573,
+                                    "self": 6.98783421805615,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 7.5769756149996965,
-                                            "count": 6024,
-                                            "self": 7.5769756149996965
+                                            "total": 89.51139365491645,
+                                            "count": 71875,
+                                            "self": 89.51139365491645
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.07345552900164876,
-                                    "count": 6088,
+                                    "total": 0.8961609959604857,
+                                    "count": 72572,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 70.61497936700493,
-                                            "count": 6088,
+                                            "total": 3605.7992072760235,
+                                            "count": 72572,
                                             "is_parallel": true,
-                                            "self": 36.15679609600738,
+                                            "self": 3190.863189739011,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0010717320000139807,
+                                                            "total": 0.0009796609999739303,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003343070000028092,
+                                                            "self": 0.00028537099990444403,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0007374250000111715,
+                                                                    "total": 0.0006942900000694863,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0007374250000111715
+                                                                    "self": 0.0006942900000694863
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.04455907400006254,
+                                                            "total": 0.03005337599995528,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003446940002049814,
+                                                            "self": 0.00034108799991372507,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0002788729999565476,
+                                                                    "total": 0.0002267160000428703,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002788729999565476
+                                                                    "self": 0.0002267160000428703
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.04314135399999941,
+                                                                    "total": 0.028759551999996802,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.04314135399999941
+                                                                    "self": 0.028759551999996802
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007941529999015984,
+                                                                    "total": 0.0007260200000018813,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002647669997486446,
+                                                                    "self": 0.00021467599992774922,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0005293860001529538,
+                                                                            "total": 0.0005113440000741321,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0005293860001529538
+                                                                            "self": 0.0005113440000741321
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 34.45818327099755,
-                                                    "count": 6087,
+                                                    "total": 414.9360175370126,
+                                                    "count": 72571,
                                                     "is_parallel": true,
-                                                    "self": 1.044178872995758,
+                                                    "self": 12.123275139162388,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 2.2722826149989714,
-                                                            "count": 6087,
+                                                            "total": 26.367381723899598,
+                                                            "count": 72571,
                                                             "is_parallel": true,
-                                                            "self": 2.2722826149989714
+                                                            "self": 26.367381723899598
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 28.658322710999983,
-                                                            "count": 6087,
+                                                            "total": 347.47698185493687,
+                                                            "count": 72571,
                                                             "is_parallel": true,
-                                                            "self": 28.658322710999983
+                                                            "self": 347.47698185493687
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 2.4833990720028396,
-                                                            "count": 6087,
+                                                            "total": 28.968378819013765,
+                                                            "count": 72571,
                                                             "is_parallel": true,
-                                                            "self": 0.9944330120011955,
+                                                            "self": 11.605077786976494,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 1.488966060001644,
-                                                                    "count": 12174,
+                                                                    "total": 17.36330103203727,
+                                                                    "count": 145142,
                                                                     "is_parallel": true,
-                                                                    "self": 1.488966060001644
+                                                                    "self": 17.36330103203727
                                                                 }
                                                             }
                                                         }
@@ -161,24 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 10.756811815003744,
-                            "count": 6088,
-                            "self": 0.17471891500701986,
+                            "total": 2989.061111625065,
+                            "count": 72572,
+                            "self": 2.1907922180675996,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 2.4880050469968182,
-                                    "count": 6088,
-                                    "self": 2.4880050469968182
+                                    "total": 33.179333187996804,
+                                    "count": 72572,
+                                    "self": 32.685874117996605,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.49345907000019906,
+                                            "count": 3,
+                                            "self": 0.49345907000019906
+                                        }
+                                    }
                                 },
                                 "_update_policy": {
-                                    "total": 8.094087852999905,
-                                    "count": 2,
-                                    "self": 6.849683180999705,
+                                    "total": 2953.690986219001,
+                                    "count": 30,
+                                    "self": 2378.3034116300378,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 1.2444046720002007,
-                                            "count": 60,
-                                            "self": 1.2444046720002007
+                                            "total": 575.387574588963,
+                                            "count": 48000,
+                                            "self": 575.387574588963
                                         }
                                     }
                                 }
@@ -187,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.999000005525886e-06,
+                    "total": 1.4380002539837733e-06,
                     "count": 1,
-                    "self": 1.999000005525886e-06
+                    "self": 1.4380002539837733e-06
                 },
                 "TrainerController._save_models": {
-                    "total": 0.385131036999951,
+                    "total": 0.2396866629997021,
                     "count": 1,
-                    "self": 0.002722564999999122,
+                    "self": 0.004467471999305417,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.38240847199995187,
+                            "total": 0.23521919100039668,
                             "count": 1,
-                            "self": 0.38240847199995187
+                            "self": 0.23521919100039668
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,49 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 48977,
-                "file_path": "results/Huggy/Huggy/Huggy-48977.onnx",
-                "reward": 2.0897797213660345,
-                "creation_time": 1679321194.6292207,
+                "steps": 199704,
+                "file_path": "results/Huggy/Huggy/Huggy-199704.onnx",
+                "reward": 3.0943431153893473,
+                "creation_time": 1679471044.4947164,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-48977.pt"
+                    "results/Huggy/Huggy/Huggy-199704.pt"
+                ]
+            },
+            {
+                "steps": 399436,
+                "file_path": "results/Huggy/Huggy/Huggy-399436.onnx",
+                "reward": -2.1291646994650364,
+                "creation_time": 1679472230.6567485,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-399436.pt"
+                ]
+            },
+            {
+                "steps": 599365,
+                "file_path": "results/Huggy/Huggy/Huggy-599365.onnx",
+                "reward": -2.1034353372330465,
+                "creation_time": 1679473319.8183784,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-599365.pt"
+                ]
+            },
+            {
+                "steps": 639115,
+                "file_path": "results/Huggy/Huggy/Huggy-639115.onnx",
+                "reward": -3.980861658602953,
+                "creation_time": 1679473559.8596787,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-639115.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 48977,
+            "steps": 639115,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 2.0897797213660345,
-            "creation_time": 1679321194.6292207,
+            "reward": -3.980861658602953,
+            "creation_time": 1679473559.8596787,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-48977.pt"
+                "results/Huggy/Huggy/Huggy-639115.pt"
             ]
         }
     },