| { |
| "name": "root", |
| "gauges": { |
| "SnowballTarget.Policy.Entropy.mean": { |
| "value": 0.9127206206321716, |
| "min": 0.9127206206321716, |
| "max": 2.8540291786193848, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Entropy.sum": { |
| "value": 8714.65625, |
| "min": 8714.65625, |
| "max": 29259.5078125, |
| "count": 20 |
| }, |
| "SnowballTarget.Step.mean": { |
| "value": 199984.0, |
| "min": 9952.0, |
| "max": 199984.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Step.sum": { |
| "value": 199984.0, |
| "min": 9952.0, |
| "max": 199984.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { |
| "value": 12.787672996520996, |
| "min": 0.3660995662212372, |
| "max": 12.787672996520996, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { |
| "value": 2493.59619140625, |
| "min": 71.0233154296875, |
| "max": 2576.17822265625, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.mean": { |
| "value": 199.0, |
| "min": 199.0, |
| "max": 199.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.EpisodeLength.sum": { |
| "value": 8756.0, |
| "min": 8756.0, |
| "max": 10945.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.mean": { |
| "value": 0.06991628462670704, |
| "min": 0.06352929391947577, |
| "max": 0.07643422782947548, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.PolicyLoss.sum": { |
| "value": 0.27966513850682817, |
| "min": 0.2541171756779031, |
| "max": 0.37595261055542445, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.mean": { |
| "value": 0.18796301932603704, |
| "min": 0.1294068417388617, |
| "max": 0.3077254613824919, |
| "count": 20 |
| }, |
| "SnowballTarget.Losses.ValueLoss.sum": { |
| "value": 0.7518520773041482, |
| "min": 0.5176273669554468, |
| "max": 1.521619098443611, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.LearningRate.mean": { |
| "value": 8.082097306000005e-06, |
| "min": 8.082097306000005e-06, |
| "max": 0.000291882002706, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.LearningRate.sum": { |
| "value": 3.232838922400002e-05, |
| "min": 3.232838922400002e-05, |
| "max": 0.00138516003828, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Epsilon.mean": { |
| "value": 0.10269400000000001, |
| "min": 0.10269400000000001, |
| "max": 0.19729400000000002, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Epsilon.sum": { |
| "value": 0.41077600000000003, |
| "min": 0.41077600000000003, |
| "max": 0.96172, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Beta.mean": { |
| "value": 0.0001444306000000001, |
| "min": 0.0001444306000000001, |
| "max": 0.0048649706, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.Beta.sum": { |
| "value": 0.0005777224000000004, |
| "min": 0.0005777224000000004, |
| "max": 0.023089828, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.mean": { |
| "value": 24.886363636363637, |
| "min": 3.5454545454545454, |
| "max": 25.145454545454545, |
| "count": 20 |
| }, |
| "SnowballTarget.Environment.CumulativeReward.sum": { |
| "value": 1095.0, |
| "min": 156.0, |
| "max": 1383.0, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.mean": { |
| "value": 24.886363636363637, |
| "min": 3.5454545454545454, |
| "max": 25.145454545454545, |
| "count": 20 |
| }, |
| "SnowballTarget.Policy.ExtrinsicReward.sum": { |
| "value": 1095.0, |
| "min": 156.0, |
| "max": 1383.0, |
| "count": 20 |
| }, |
| "SnowballTarget.IsTraining.mean": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 20 |
| }, |
| "SnowballTarget.IsTraining.sum": { |
| "value": 1.0, |
| "min": 1.0, |
| "max": 1.0, |
| "count": 20 |
| } |
| }, |
| "metadata": { |
| "timer_format_version": "0.1.0", |
| "start_time_seconds": "1720730739", |
| "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]", |
| "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", |
| "mlagents_version": "1.1.0.dev0", |
| "mlagents_envs_version": "1.1.0.dev0", |
| "communication_protocol_version": "1.5.0", |
| "pytorch_version": "2.3.0+cu121", |
| "numpy_version": "1.23.5", |
| "end_time_seconds": "1720731307" |
| }, |
| "total": 567.972088899, |
| "count": 1, |
| "self": 0.5370770910001283, |
| "children": { |
| "run_training.setup": { |
| "total": 0.07561467400000765, |
| "count": 1, |
| "self": 0.07561467400000765 |
| }, |
| "TrainerController.start_learning": { |
| "total": 567.3593971339999, |
| "count": 1, |
| "self": 0.7589781389953032, |
| "children": { |
| "TrainerController._reset_env": { |
| "total": 3.607555400000024, |
| "count": 1, |
| "self": 3.607555400000024 |
| }, |
| "TrainerController.advance": { |
| "total": 562.8954089350048, |
| "count": 18202, |
| "self": 0.4045583549961975, |
| "children": { |
| "env_step": { |
| "total": 562.4908505800086, |
| "count": 18202, |
| "self": 433.5176628369991, |
| "children": { |
| "SubprocessEnvManager._take_step": { |
| "total": 128.57580469500977, |
| "count": 18202, |
| "self": 2.164082026011897, |
| "children": { |
| "TorchPolicy.evaluate": { |
| "total": 126.41172266899787, |
| "count": 18202, |
| "self": 126.41172266899787 |
| } |
| } |
| }, |
| "workers": { |
| "total": 0.39738304799971047, |
| "count": 18202, |
| "self": 0.0, |
| "children": { |
| "worker_root": { |
| "total": 565.5422048910057, |
| "count": 18202, |
| "is_parallel": true, |
| "self": 264.4579810280188, |
| "children": { |
| "run_training.setup": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "steps_from_proto": { |
| "total": 0.0067542249998950865, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.004333691999931943, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002420532999963143, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.002420532999963143 |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 0.04456802700008211, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0011523580000130096, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 0.0004998940000859875, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.0004998940000859875 |
| }, |
| "communicator.exchange": { |
| "total": 0.040400653999995484, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.040400653999995484 |
| }, |
| "steps_from_proto": { |
| "total": 0.00251512099998763, |
| "count": 1, |
| "is_parallel": true, |
| "self": 0.00048362900008669385, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 0.002031491999900936, |
| "count": 10, |
| "is_parallel": true, |
| "self": 0.002031491999900936 |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "UnityEnvironment.step": { |
| "total": 301.08422386298685, |
| "count": 18201, |
| "is_parallel": true, |
| "self": 14.394372078962647, |
| "children": { |
| "UnityEnvironment._generate_step_input": { |
| "total": 7.519843081995646, |
| "count": 18201, |
| "is_parallel": true, |
| "self": 7.519843081995646 |
| }, |
| "communicator.exchange": { |
| "total": 234.9965257140109, |
| "count": 18201, |
| "is_parallel": true, |
| "self": 234.9965257140109 |
| }, |
| "steps_from_proto": { |
| "total": 44.17348298801767, |
| "count": 18201, |
| "is_parallel": true, |
| "self": 8.676721419966157, |
| "children": { |
| "_process_rank_one_or_two_observation": { |
| "total": 35.49676156805151, |
| "count": 182010, |
| "is_parallel": true, |
| "self": 35.49676156805151 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "trainer_threads": { |
| "total": 0.00020884399987153301, |
| "count": 1, |
| "self": 0.00020884399987153301, |
| "children": { |
| "thread_root": { |
| "total": 0.0, |
| "count": 0, |
| "is_parallel": true, |
| "self": 0.0, |
| "children": { |
| "trainer_advance": { |
| "total": 556.1399468851216, |
| "count": 758376, |
| "is_parallel": true, |
| "self": 16.846609545113438, |
| "children": { |
| "process_trajectory": { |
| "total": 302.54633174000935, |
| "count": 758376, |
| "is_parallel": true, |
| "self": 301.38680463100945, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 1.159527108999896, |
| "count": 4, |
| "is_parallel": true, |
| "self": 1.159527108999896 |
| } |
| } |
| }, |
| "_update_policy": { |
| "total": 236.74700559999883, |
| "count": 90, |
| "is_parallel": true, |
| "self": 70.16763046799383, |
| "children": { |
| "TorchPPOOptimizer.update": { |
| "total": 166.579375132005, |
| "count": 4587, |
| "is_parallel": true, |
| "self": 166.579375132005 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
| }, |
| "TrainerController._save_models": { |
| "total": 0.09724581599994053, |
| "count": 1, |
| "self": 0.0011363600001459417, |
| "children": { |
| "RLTrainer._checkpoint": { |
| "total": 0.09610945599979459, |
| "count": 1, |
| "self": 0.09610945599979459 |
| } |
| } |
| } |
| } |
| } |
| } |
| } |
