{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.881080687046051, "min": 0.881080687046051, "max": 2.8586106300354004, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8412.55859375, "min": 8412.55859375, "max": 29275.03125, "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": 12.929838180541992, "min": 0.30054256319999695, "max": 12.929838180541992, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2521.318359375, "min": 58.305259704589844, "max": 2593.6591796875, "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": 0.06284684776944108, "min": 0.06232375071383156, "max": 0.07502825723763545, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2513873910777643, "min": 0.24929500285532624, "max": 0.3655688802748188, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19313890501564623, "min": 0.10473075441162413, "max": 0.2729351578389897, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7725556200625849, "min": 0.41892301764649653, "max": 1.3646757891949486, "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": 25.90909090909091, "min": 3.0681818181818183, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 135.0, "max": 1413.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.0681818181818183, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 135.0, "max": 1413.0, "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": "1678105148", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.22.4", "end_time_seconds": "1678105619" }, "total": 471.05753810600004, "count": 1, "self": 0.4419507130000966, "children": { "run_training.setup": { "total": 0.12023521999998366, "count": 1, "self": 0.12023521999998366 }, "TrainerController.start_learning": { "total": 470.49535217299996, "count": 1, "self": 0.5420162400044433, "children": { "TrainerController._reset_env": { "total": 9.256121838000013, "count": 1, "self": 9.256121838000013 }, "TrainerController.advance": { "total": 460.5778809049955, "count": 18202, "self": 0.29489622099720236, "children": { "env_step": { "total": 460.2829846839983, "count": 18202, "self": 315.3490162670012, "children": { "SubprocessEnvManager._take_step": { "total": 144.66113875899788, "count": 18202, "self": 1.6661593600003357, "children": { "TorchPolicy.evaluate": { "total": 142.99497939899754, "count": 18202, "self": 31.76165663200169, "children": { "TorchPolicy.sample_actions": { "total": 111.23332276699585, "count": 18202, "self": 111.23332276699585 } } } } }, "workers": { "total": 0.272829657999182, "count": 18202, "self": 0.0, "children": { "worker_root": { "total": 468.98739979200366, "count": 18202, "is_parallel": true, "self": 228.51237087799785, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004754767000008542, "count": 1, "is_parallel": true, "self": 0.0034303650000993002, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013244019999092416, "count": 10, "is_parallel": true, "self": 0.0013244019999092416 } } }, "UnityEnvironment.step": { "total": 0.04974629299999833, "count": 1, "is_parallel": true, "self": 0.0005505949999360382, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028072399999246045, "count": 1, "is_parallel": true, "self": 0.00028072399999246045 }, "communicator.exchange": { "total": 0.047146701000031044, "count": 1, "is_parallel": true, "self": 0.047146701000031044 }, "steps_from_proto": { "total": 0.0017682730000387892, "count": 1, "is_parallel": true, "self": 0.0004090520000659126, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013592209999728766, "count": 10, "is_parallel": true, "self": 0.0013592209999728766 } } } } } } }, "UnityEnvironment.step": { "total": 240.4750289140058, "count": 18201, "is_parallel": true, "self": 9.690791480012251, "children": { "UnityEnvironment._generate_step_input": { "total": 5.2390000010017275, "count": 18201, "is_parallel": true, "self": 5.2390000010017275 }, "communicator.exchange": { "total": 193.70833826999706, "count": 18201, "is_parallel": true, "self": 193.70833826999706 }, "steps_from_proto": { "total": 31.83689916299477, "count": 18201, "is_parallel": true, "self": 6.94763855897304, "children": { "_process_rank_one_or_two_observation": { "total": 24.88926060402173, "count": 182010, "is_parallel": true, "self": 24.88926060402173 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011276600002929626, "count": 1, "self": 0.00011276600002929626, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 457.1228562780022, "count": 402619, "is_parallel": true, "self": 10.094085275016596, "children": { "process_trajectory": { "total": 259.370335557986, "count": 402619, "is_parallel": true, "self": 258.20618920598605, "children": { "RLTrainer._checkpoint": { "total": 1.164146351999932, "count": 4, "is_parallel": true, "self": 1.164146351999932 } } }, "_update_policy": { "total": 187.6584354449996, "count": 90, "is_parallel": true, "self": 66.97974957500651, "children": { "TorchPPOOptimizer.update": { "total": 120.6786858699931, "count": 4587, "is_parallel": true, "self": 120.6786858699931 } } } } } } } } }, "TrainerController._save_models": { "total": 0.119220423999991, "count": 1, "self": 0.0008138389999885476, "children": { "RLTrainer._checkpoint": { "total": 0.11840658500000245, "count": 1, "self": 0.11840658500000245 } } } } } } }