add ppo snowballtarget agent

SnowballTarget.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2664a2e0bcdb531977baa711c0df6ae87da487202412deb82efa02edc3eb1035
+oid sha256:8853c2a028cef293a4cc786e8d35c60fc2e75117ad45527472a09bc755d98659
 size 646532

SnowballTarget/{SnowballTarget-1408.onnx → SnowballTarget-49936.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2664a2e0bcdb531977baa711c0df6ae87da487202412deb82efa02edc3eb1035
+oid sha256:6b1a680c8a3eae1e9e55edd425b5a1e6863b81b739ef70d19e0980f445d423e4
 size 646532

SnowballTarget/{SnowballTarget-1408.pt → SnowballTarget-49936.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab04bf0dde56903d2a488a656a06464d5b3bbe4f9558102f5bf29e3b2fe79c71
-size 1285152
+oid sha256:3b50b9f9d96ce559db17e730434d3bf0f16739b7bd35f1e8f21dda629853aed6
+size 3843968

SnowballTarget/SnowballTarget-60104.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8853c2a028cef293a4cc786e8d35c60fc2e75117ad45527472a09bc755d98659
+size 646532

SnowballTarget/SnowballTarget-60104.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a540ceb8966198116d14f1762072fb5a81c12f8c52a3a9b4e5d6b55eb1a51385
+size 3843968

SnowballTarget/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab04bf0dde56903d2a488a656a06464d5b3bbe4f9558102f5bf29e3b2fe79c71
-size 1285152
+oid sha256:a540ceb8966198116d14f1762072fb5a81c12f8c52a3a9b4e5d6b55eb1a51385
+size 3843968

SnowballTarget/{events.out.tfevents.1680784150.f5f04898c26b.966.0 → events.out.tfevents.1680784929.50ee6e3d3587.973.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acfabee5b543c6b037e5f94d2538922729cda60e3bc1c3006e37a132b69e102e
-size 1112
+oid sha256:22a138270fb14b13d56b1586ed96d1043beb343bddff8362e7ab0af0353bd141
+size 12355

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 1000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SnowballTarget": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "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": 50000, "network_settings": {"normalize": false, "hidden_units": 256, "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}}}, "init_path": null, "keep_checkpoints": 10, "even_checkpoints": false, "max_steps": 60000, "time_horizon": 64, "summary_freq": 10000, "threaded": true, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/SnowballTarget/SnowballTarget", "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": "SnowballTarget1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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: 10
     even_checkpoints: false
-    max_steps: 1000
+    max_steps: 60000
     time_horizon: 64
     summary_freq: 10000
     threaded: true

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  0.089 seconds
+- Completed reload, in  0.087 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)
@@ -45,7 +45,7 @@ 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: 0.598937 ms
+UnloadTime: 0.654828 ms
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
@@ -53,7 +53,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 39 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 1614 frames, [16.0 KB-32.0 KB]: 27 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
@@ -169,22 +169,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 20
+  Peak main deferred allocation count 41
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 40 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1642 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 4.7 MB
+      Peak Allocated memory 6.2 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 40 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1642 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.8 MB
+      Peak Allocated memory 17.3 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -213,13 +213,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 31 frames, [64.0 KB-128.0 KB]: 9 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1144 frames, [64.0 KB-128.0 KB]: 498 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 65.6 KB
+      Peak Allocated memory 67.3 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 40 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1642 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 39.6 KB
@@ -231,13 +231,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 40 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1642 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1641 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 MB
@@ -249,13 +249,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.0 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 40 frames
+      Peak usage frame count: [0-1.0 KB]: 1642 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]: 40 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1642 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.7 KB

run_logs/timers.json

@@ -1,8 +1,154 @@
 {
     "name": "root",
+    "gauges": {
+        "SnowballTarget.Policy.Entropy.mean": {
+            "value": 2.2936456203460693,
+            "min": 2.2936456203460693,
+            "max": 2.866025924682617,
+            "count": 6
+        },
+        "SnowballTarget.Policy.Entropy.sum": {
+            "value": 22152.029296875,
+            "min": 22152.029296875,
+            "max": 29350.97265625,
+            "count": 6
+        },
+        "SnowballTarget.Step.mean": {
+            "value": 59976.0,
+            "min": 9952.0,
+            "max": 59976.0,
+            "count": 6
+        },
+        "SnowballTarget.Step.sum": {
+            "value": 59976.0,
+            "min": 9952.0,
+            "max": 59976.0,
+            "count": 6
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 4.7627153396606445,
+            "min": 0.34516000747680664,
+            "max": 4.7627153396606445,
+            "count": 6
+        },
+        "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 976.3566284179688,
+            "min": 66.96104431152344,
+            "max": 976.3566284179688,
+            "count": 6
+        },
+        "SnowballTarget.Environment.EpisodeLength.mean": {
+            "value": 199.0,
+            "min": 199.0,
+            "max": 199.0,
+            "count": 6
+        },
+        "SnowballTarget.Environment.EpisodeLength.sum": {
+            "value": 10945.0,
+            "min": 8756.0,
+            "max": 10945.0,
+            "count": 6
+        },
+        "SnowballTarget.Losses.PolicyLoss.mean": {
+            "value": 0.06690161215568272,
+            "min": 0.062435699654765905,
+            "max": 0.07468453972643485,
+            "count": 6
+        },
+        "SnowballTarget.Losses.PolicyLoss.sum": {
+            "value": 0.33450806077841355,
+            "min": 0.24974279861906362,
+            "max": 0.34266459971010643,
+            "count": 6
+        },
+        "SnowballTarget.Losses.ValueLoss.mean": {
+            "value": 0.2576114994638106,
+            "min": 0.12173185954281293,
+            "max": 0.2876496722593027,
+            "count": 6
+        },
+        "SnowballTarget.Losses.ValueLoss.sum": {
+            "value": 1.288057497319053,
+            "min": 0.4869274381712517,
+            "max": 1.3561888936103559,
+            "count": 6
+        },
+        "SnowballTarget.Policy.LearningRate.mean": {
+            "value": 2.544009152e-05,
+            "min": 2.544009152e-05,
+            "max": 0.00027294000901999997,
+            "count": 6
+        },
+        "SnowballTarget.Policy.LearningRate.sum": {
+            "value": 0.0001272004576,
+            "min": 0.0001272004576,
+            "max": 0.0011172001276,
+            "count": 6
+        },
+        "SnowballTarget.Policy.Epsilon.mean": {
+            "value": 0.10848000000000002,
+            "min": 0.10848000000000002,
+            "max": 0.19098,
+            "count": 6
+        },
+        "SnowballTarget.Policy.Epsilon.sum": {
+            "value": 0.5424000000000001,
+            "min": 0.49992000000000014,
+            "max": 0.8724000000000001,
+            "count": 6
+        },
+        "SnowballTarget.Policy.Beta.mean": {
+            "value": 0.0004331519999999999,
+            "min": 0.0004331519999999999,
+            "max": 0.004549902,
+            "count": 6
+        },
+        "SnowballTarget.Policy.Beta.sum": {
+            "value": 0.0021657599999999996,
+            "min": 0.0021657599999999996,
+            "max": 0.01863276,
+            "count": 6
+        },
+        "SnowballTarget.Environment.CumulativeReward.mean": {
+            "value": 11.345454545454546,
+            "min": 3.522727272727273,
+            "max": 11.345454545454546,
+            "count": 6
+        },
+        "SnowballTarget.Environment.CumulativeReward.sum": {
+            "value": 624.0,
+            "min": 155.0,
+            "max": 624.0,
+            "count": 6
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.mean": {
+            "value": 11.345454545454546,
+            "min": 3.522727272727273,
+            "max": 11.345454545454546,
+            "count": 6
+        },
+        "SnowballTarget.Policy.ExtrinsicReward.sum": {
+            "value": 624.0,
+            "min": 155.0,
+            "max": 624.0,
+            "count": 6
+        },
+        "SnowballTarget.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 6
+        },
+        "SnowballTarget.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 6
+        }
+    },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1680784149",
+        "start_time_seconds": "1680784928",
         "python_version": "3.10.5 | packaged by conda-forge | (main, Jun 14 2022, 07:04:59) [GCC 10.3.0]",
         "command_line_arguments": "ml-agents/mlagents/trainers/learn.py ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
         "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": "1680784156"
+        "end_time_seconds": "1680785074"
     },
-    "total": 7.037014824999915,
+    "total": 145.45940288200018,
     "count": 1,
-    "self": 0.5127422909997676,
+    "self": 0.48453295000035723,
     "children": {
         "run_training.setup": {
-            "total": 0.0196718580000379,
+            "total": 0.021707205999973667,
             "count": 1,
-            "self": 0.0196718580000379
+            "self": 0.021707205999973667
         },
         "TrainerController.start_learning": {
-            "total": 6.504600676000109,
+            "total": 144.95316272599985,
             "count": 1,
-            "self": 0.028221422998058188,
+            "self": 0.16149714400512494,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 3.2124334480001835,
+                    "total": 3.113833035000198,
                     "count": 1,
-                    "self": 3.2124334480001835
+                    "self": 3.113833035000198
                 },
                 "TrainerController.advance": {
-                    "total": 2.952782744001752,
-                    "count": 131,
-                    "self": 0.0019149590036704467,
+                    "total": 141.46736615899476,
+                    "count": 5471,
+                    "self": 0.07663059798960603,
                     "children": {
                         "env_step": {
-                            "total": 2.9508677849980813,
-                            "count": 131,
-                            "self": 2.3390354029995706,
+                            "total": 141.39073556100516,
+                            "count": 5471,
+                            "self": 101.17150663101233,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 0.6098573089998354,
-                                    "count": 131,
-                                    "self": 0.009847335000131352,
+                                    "total": 40.136498686992354,
+                                    "count": 5471,
+                                    "self": 0.5052758879951398,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 0.600009973999704,
-                                            "count": 131,
-                                            "self": 0.600009973999704
+                                            "total": 39.631222798997214,
+                                            "count": 5471,
+                                            "self": 39.631222798997214
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 0.0019750729986753868,
-                                    "count": 131,
+                                    "total": 0.08273024300046927,
+                                    "count": 5471,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 6.177824511000836,
-                                            "count": 131,
+                                            "total": 144.3440517189972,
+                                            "count": 5471,
                                             "is_parallel": true,
-                                            "self": 4.207890857000621,
+                                            "self": 65.2818101589994,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -71,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0020833740002217382,
+                                                            "total": 0.001980684000045585,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0006434789995637402,
+                                                            "self": 0.0006041300000561023,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001439895000657998,
+                                                                    "total": 0.0013765539999894827,
                                                                     "count": 10,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001439895000657998
+                                                                    "self": 0.0013765539999894827
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.05380231999993157,
+                                                            "total": 0.08273509900004683,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00039890099992589967,
+                                                            "self": 0.0005849889998899016,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0003473599999779253,
+                                                                    "total": 0.0003496950000680954,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0003473599999779253
+                                                                    "self": 0.0003496950000680954
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.05078761699996903,
+                                                                    "total": 0.07961141800001315,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.05078761699996903
+                                                                    "self": 0.07961141800001315
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0022684420000587124,
+                                                                    "total": 0.0021889970000756875,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00043957899993074534,
+                                                                    "self": 0.00044234500091988593,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.001828863000127967,
+                                                                            "total": 0.0017466519991558016,
                                                                             "count": 10,
                                                                             "is_parallel": true,
-                                                                            "self": 0.001828863000127967
+                                                                            "self": 0.0017466519991558016
                                                                         }
                                                                     }
                                                                 }
@@ -121,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1.969933654000215,
-                                                    "count": 130,
+                                                    "total": 79.0622415599978,
+                                                    "count": 5470,
                                                     "is_parallel": true,
-                                                    "self": 0.0699027690022831,
+                                                    "self": 2.8316271569817673,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 0.048496131998490455,
-                                                            "count": 130,
+                                                            "total": 1.7115460930017434,
+                                                            "count": 5470,
                                                             "is_parallel": true,
-                                                            "self": 0.048496131998490455
+                                                            "self": 1.7115460930017434
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1.6077250019980056,
-                                                            "count": 130,
+                                                            "total": 64.90729787000214,
+                                                            "count": 5470,
                                                             "is_parallel": true,
-                                                            "self": 1.6077250019980056
+                                                            "self": 64.90729787000214
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 0.24380975100143587,
-                                                            "count": 130,
+                                                            "total": 9.611770440012151,
+                                                            "count": 5470,
                                                             "is_parallel": true,
-                                                            "self": 0.04959121400065669,
+                                                            "self": 1.9485815850021027,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.19421853700077918,
-                                                                    "count": 1300,
+                                                                    "total": 7.663188855010048,
+                                                                    "count": 54700,
                                                                     "is_parallel": true,
-                                                                    "self": 0.19421853700077918
+                                                                    "self": 7.663188855010048
                                                                 }
                                                             }
                                                         }
@@ -163,9 +309,9 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 2.3585000008097268e-05,
+                    "total": 0.0001451719999749912,
                     "count": 1,
-                    "self": 2.3585000008097268e-05,
+                    "self": 0.0001451719999749912,
                     "children": {
                         "thread_root": {
                             "total": 0.0,
@@ -174,16 +320,38 @@
                             "self": 0.0,
                             "children": {
                                 "trainer_advance": {
-                                    "total": 2.9356368650082914,
-                                    "count": 4398,
+                                    "total": 140.48691986093695,
+                                    "count": 114276,
                                     "is_parallel": true,
-                                    "self": 0.09288661300911372,
+                                    "self": 2.6478413979371,
                                     "children": {
                                         "process_trajectory": {
-                                            "total": 2.8427502519991776,
-                                            "count": 4398,
+                                            "total": 78.75249613300025,
+                                            "count": 114276,
                                             "is_parallel": true,
-                                            "self": 2.8427502519991776
+                                            "self": 78.52266481600032,
+                                            "children": {
+                                                "RLTrainer._checkpoint": {
+                                                    "total": 0.22983131699993464,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.22983131699993464
+                                                }
+                                            }
+                                        },
+                                        "_update_policy": {
+                                            "total": 59.0865823299996,
+                                            "count": 27,
+                                            "is_parallel": true,
+                                            "self": 16.2498989529995,
+                                            "children": {
+                                                "TorchPPOOptimizer.update": {
+                                                    "total": 42.8366833770001,
+                                                    "count": 1374,
+                                                    "is_parallel": true,
+                                                    "self": 42.8366833770001
+                                                }
+                                            }
                                         }
                                     }
                                 }
@@ -192,14 +360,14 @@
                     }
                 },
                 "TrainerController._save_models": {
-                    "total": 0.3111394760001076,
+                    "total": 0.21032121599978382,
                     "count": 1,
-                    "self": 0.0013675610000518645,
+                    "self": 0.0012572019998060568,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.30977191500005574,
+                            "total": 0.20906401399997776,
                             "count": 1,
-                            "self": 0.30977191500005574
+                            "self": 0.20906401399997776
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,22 +2,31 @@
     "SnowballTarget": {
         "checkpoints": [
             {
-                "steps": 1408,
-                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-1408.onnx",
-                "reward": null,
-                "creation_time": 1680784156.2640371,
+                "steps": 49936,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.onnx",
+                "reward": 10.818181818181818,
+                "creation_time": 1680785050.0995784,
                 "auxillary_file_paths": [
-                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-1408.pt"
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-49936.pt"
+                ]
+            },
+            {
+                "steps": 60104,
+                "file_path": "results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.onnx",
+                "reward": 12.454545454545455,
+                "creation_time": 1680785073.8293626,
+                "auxillary_file_paths": [
+                    "results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 1408,
+            "steps": 60104,
             "file_path": "results/SnowballTarget1/SnowballTarget.onnx",
-            "reward": null,
-            "creation_time": 1680784156.2640371,
+            "reward": 12.454545454545455,
+            "creation_time": 1680785073.8293626,
             "auxillary_file_paths": [
-                "results/SnowballTarget1/SnowballTarget/SnowballTarget-1408.pt"
+                "results/SnowballTarget1/SnowballTarget/SnowballTarget-60104.pt"
             ]
         }
     },