{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.801628828048706, "min": 0.801628828048706, "max": 2.8685519695281982, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7653.9521484375, "min": 7653.9521484375, "max": 29439.94921875, "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": 13.030939102172852, "min": 0.4070104658603668, "max": 13.030939102172852, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2541.033203125, "min": 78.96002960205078, "max": 2643.24609375, "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": 0.0643797250500876, "min": 0.05993595138733879, "max": 0.07682173041607979, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2575189002003504, "min": 0.23974380554935515, "max": 0.353524929435248, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.23538489727412953, "min": 0.116534513195374, "max": 0.2886992642108132, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9415395890965181, "min": 0.466138052781496, "max": 1.4434963210540661, "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": 25.477272727272727, "min": 3.3863636363636362, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 149.0, "max": 1421.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.3863636363636362, "max": 25.836363636363636, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 149.0, "max": 1421.0, "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": "1679999388", "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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "0.31.0.dev0", "mlagents_envs_version": "0.31.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.11.0+cu102", "numpy_version": "1.21.2", "end_time_seconds": "1679999879" }, "total": 491.39173063799996, "count": 1, "self": 0.4300983079999696, "children": { "run_training.setup": { "total": 0.11606534599997076, "count": 1, "self": 0.11606534599997076 }, "TrainerController.start_learning": { "total": 490.845566984, "count": 1, "self": 0.588394634995268, "children": { "TrainerController._reset_env": { "total": 8.668825276000007, "count": 1, "self": 8.668825276000007 }, "TrainerController.advance": { "total": 481.4518965340047, "count": 18201, "self": 0.29653230800323627, "children": { "env_step": { "total": 481.15536422600144, "count": 18201, "self": 345.63200502800413, "children": { "SubprocessEnvManager._take_step": { "total": 135.24176936400045, "count": 18201, "self": 1.9199816140048256, "children": { "TorchPolicy.evaluate": { "total": 133.32178774999562, "count": 18201, "self": 133.32178774999562 } } }, "workers": { "total": 0.2815898339968612, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 489.11784374299646, "count": 18201, "is_parallel": true, "self": 233.9178435360052, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007775340000023334, "count": 1, "is_parallel": true, "self": 0.005447205999985272, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023281340000380624, "count": 10, "is_parallel": true, "self": 0.0023281340000380624 } } }, "UnityEnvironment.step": { "total": 0.10605864900003326, "count": 1, "is_parallel": true, "self": 0.0005870760001016606, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004122769999526099, "count": 1, "is_parallel": true, "self": 0.0004122769999526099 }, "communicator.exchange": { "total": 0.10320134099998768, "count": 1, "is_parallel": true, "self": 0.10320134099998768 }, "steps_from_proto": { "total": 0.001857954999991307, "count": 1, "is_parallel": true, "self": 0.00039101599992363845, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014669390000676685, "count": 10, "is_parallel": true, "self": 0.0014669390000676685 } } } } } } }, "UnityEnvironment.step": { "total": 255.20000020699126, "count": 18200, "is_parallel": true, "self": 10.06516112497519, "children": { "UnityEnvironment._generate_step_input": { "total": 5.548940923005887, "count": 18200, "is_parallel": true, "self": 5.548940923005887 }, "communicator.exchange": { "total": 205.98332945099958, "count": 18200, "is_parallel": true, "self": 205.98332945099958 }, "steps_from_proto": { "total": 33.60256870801061, "count": 18200, "is_parallel": true, "self": 6.8158489990179305, "children": { "_process_rank_one_or_two_observation": { "total": 26.786719708992678, "count": 182000, "is_parallel": true, "self": 26.786719708992678 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00013427500005036563, "count": 1, "self": 0.00013427500005036563, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 477.72833348301475, "count": 430964, "is_parallel": true, "self": 10.821693737030444, "children": { "process_trajectory": { "total": 266.2221834029849, "count": 430964, "is_parallel": true, "self": 265.3534350289849, "children": { "RLTrainer._checkpoint": { "total": 0.8687483740000062, "count": 4, "is_parallel": true, "self": 0.8687483740000062 } } }, "_update_policy": { "total": 200.6844563429994, "count": 90, "is_parallel": true, "self": 72.8615971130011, "children": { "TorchPPOOptimizer.update": { "total": 127.8228592299983, "count": 4587, "is_parallel": true, "self": 127.8228592299983 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1363162640000155, "count": 1, "self": 0.0009442629999512064, "children": { "RLTrainer._checkpoint": { "total": 0.1353720010000643, "count": 1, "self": 0.1353720010000643 } } } } } } }