{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.949034571647644, "min": 0.949034571647644, "max": 2.8746330738067627, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9082.2607421875, "min": 9082.2607421875, "max": 29439.1171875, "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": 12.795978546142578, "min": 0.43433642387390137, "max": 12.795978546142578, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2495.2158203125, "min": 84.26126861572266, "max": 2579.810546875, "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": 0.06736745188597934, "min": 0.06230979760927285, "max": 0.07623561677530374, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26946980754391736, "min": 0.2492391904370914, "max": 0.38117808387651875, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21873977407813075, "min": 0.09804878818948626, "max": 0.2771130197772792, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.874959096312523, "min": 0.39219515275794503, "max": 1.3855650988863961, "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": 25.113636363636363, "min": 3.0, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1105.0, "min": 132.0, "max": 1392.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.113636363636363, "min": 3.0, "max": 25.30909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1105.0, "min": 132.0, "max": 1392.0, "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": "1695970725", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yml --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": "1695971200" }, "total": 475.447683827, "count": 1, "self": 0.4343365479999193, "children": { "run_training.setup": { "total": 0.050883276999911686, "count": 1, "self": 0.050883276999911686 }, "TrainerController.start_learning": { "total": 474.96246400200016, "count": 1, "self": 0.5634605400057353, "children": { "TrainerController._reset_env": { "total": 5.514502194999977, "count": 1, "self": 5.514502194999977 }, "TrainerController.advance": { "total": 468.7442876009943, "count": 18203, "self": 0.27657622598189846, "children": { "env_step": { "total": 468.4677113750124, "count": 18203, "self": 341.9623152260008, "children": { "SubprocessEnvManager._take_step": { "total": 126.22328181802368, "count": 18203, "self": 1.6789795880370093, "children": { "TorchPolicy.evaluate": { "total": 124.54430222998667, "count": 18203, "self": 124.54430222998667 } } }, "workers": { "total": 0.2821143309879517, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 473.41852487098777, "count": 18203, "is_parallel": true, "self": 222.23348223096923, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005621926000003441, "count": 1, "is_parallel": true, "self": 0.004094982999959029, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015269430000444117, "count": 10, "is_parallel": true, "self": 0.0015269430000444117 } } }, "UnityEnvironment.step": { "total": 0.12452750400007062, "count": 1, "is_parallel": true, "self": 0.0006308669999270933, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000446547000137798, "count": 1, "is_parallel": true, "self": 0.000446547000137798 }, "communicator.exchange": { "total": 0.11313989099994615, "count": 1, "is_parallel": true, "self": 0.11313989099994615 }, "steps_from_proto": { "total": 0.010310199000059583, "count": 1, "is_parallel": true, "self": 0.008575948999805405, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017342500002541783, "count": 10, "is_parallel": true, "self": 0.0017342500002541783 } } } } } } }, "UnityEnvironment.step": { "total": 251.18504264001854, "count": 18202, "is_parallel": true, "self": 10.480434564023653, "children": { "UnityEnvironment._generate_step_input": { "total": 5.451341890002141, "count": 18202, "is_parallel": true, "self": 5.451341890002141 }, "communicator.exchange": { "total": 199.02783121799962, "count": 18202, "is_parallel": true, "self": 199.02783121799962 }, "steps_from_proto": { "total": 36.225434967993124, "count": 18202, "is_parallel": true, "self": 6.610645071971021, "children": { "_process_rank_one_or_two_observation": { "total": 29.614789896022103, "count": 182020, "is_parallel": true, "self": 29.614789896022103 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00016372200002479076, "count": 1, "self": 0.00016372200002479076, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 465.1179867060325, "count": 445041, "is_parallel": true, "self": 9.736447642929079, "children": { "process_trajectory": { "total": 254.3981494311031, "count": 445041, "is_parallel": true, "self": 253.57541586010302, "children": { "RLTrainer._checkpoint": { "total": 0.8227335710000716, "count": 4, "is_parallel": true, "self": 0.8227335710000716 } } }, "_update_policy": { "total": 200.98338963200035, "count": 90, "is_parallel": true, "self": 78.20234336399858, "children": { "TorchPPOOptimizer.update": { "total": 122.78104626800177, "count": 4584, "is_parallel": true, "self": 122.78104626800177 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14004994400011128, "count": 1, "self": 0.0009166430002096604, "children": { "RLTrainer._checkpoint": { "total": 0.13913330099990162, "count": 1, "self": 0.13913330099990162 } } } } } } }