{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9491671919822693, "min": 0.9491671919822693, "max": 2.873358964920044, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9062.6484375, "min": 9062.6484375, "max": 29426.0703125, "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": 13.12903881072998, "min": 0.26945894956588745, "max": 13.12903881072998, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2560.16259765625, "min": 52.2750358581543, "max": 2660.425048828125, "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": 0.06561478921317829, "min": 0.061130855948080105, "max": 0.07472354151386575, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26245915685271315, "min": 0.24452342379232042, "max": 0.3633556487726381, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18902666866779325, "min": 0.11879566900190147, "max": 0.29518817021858457, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.756106674671173, "min": 0.4751826760076059, "max": 1.4428637077411015, "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": 25.977272727272727, "min": 3.1136363636363638, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 137.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 3.1136363636363638, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 137.0, "max": 1407.0, "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": "1718823088", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=SnowballTarget2 --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": "1718823523" }, "total": 435.38469101, "count": 1, "self": 0.42509744699998464, "children": { "run_training.setup": { "total": 0.05280951599991113, "count": 1, "self": 0.05280951599991113 }, "TrainerController.start_learning": { "total": 434.9067840470001, "count": 1, "self": 0.5133155449941569, "children": { "TrainerController._reset_env": { "total": 3.635744693999982, "count": 1, "self": 3.635744693999982 }, "TrainerController.advance": { "total": 430.6674894910061, "count": 18200, "self": 0.25084436400959476, "children": { "env_step": { "total": 430.4166451269965, "count": 18200, "self": 277.91082357200503, "children": { "SubprocessEnvManager._take_step": { "total": 152.24668928001063, "count": 18200, "self": 1.3681589490223587, "children": { "TorchPolicy.evaluate": { "total": 150.87853033098827, "count": 18200, "self": 150.87853033098827 } } }, "workers": { "total": 0.2591322749808569, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 433.83057908300407, "count": 18200, "is_parallel": true, "self": 221.87660989501228, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006100631999970574, "count": 1, "is_parallel": true, "self": 0.003949216999785676, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021514150001848975, "count": 10, "is_parallel": true, "self": 0.0021514150001848975 } } }, "UnityEnvironment.step": { "total": 0.036185340999963955, "count": 1, "is_parallel": true, "self": 0.0006565009999803806, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003754869999283983, "count": 1, "is_parallel": true, "self": 0.0003754869999283983 }, "communicator.exchange": { "total": 0.033303987000067536, "count": 1, "is_parallel": true, "self": 0.033303987000067536 }, "steps_from_proto": { "total": 0.00184936599998764, "count": 1, "is_parallel": true, "self": 0.0003609860000324261, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014883799999552139, "count": 10, "is_parallel": true, "self": 0.0014883799999552139 } } } } } } }, "UnityEnvironment.step": { "total": 211.9539691879918, "count": 18199, "is_parallel": true, "self": 9.84769300998596, "children": { "UnityEnvironment._generate_step_input": { "total": 5.1511003469960315, "count": 18199, "is_parallel": true, "self": 5.1511003469960315 }, "communicator.exchange": { "total": 164.90887508299772, "count": 18199, "is_parallel": true, "self": 164.90887508299772 }, "steps_from_proto": { "total": 32.04630074801207, "count": 18199, "is_parallel": true, "self": 5.89551108901594, "children": { "_process_rank_one_or_two_observation": { "total": 26.150789658996132, "count": 181990, "is_parallel": true, "self": 26.150789658996132 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00011301099993943353, "count": 1, "self": 0.00011301099993943353, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 425.44039350006574, "count": 651317, "is_parallel": true, "self": 13.252363735073118, "children": { "process_trajectory": { "total": 235.62172986199175, "count": 651317, "is_parallel": true, "self": 234.74346981799158, "children": { "RLTrainer._checkpoint": { "total": 0.8782600440001715, "count": 4, "is_parallel": true, "self": 0.8782600440001715 } } }, "_update_policy": { "total": 176.56629990300087, "count": 90, "is_parallel": true, "self": 56.41682894500491, "children": { "TorchPPOOptimizer.update": { "total": 120.14947095799596, "count": 4587, "is_parallel": true, "self": 120.14947095799596 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09012130599990087, "count": 1, "self": 0.0009251519998088042, "children": { "RLTrainer._checkpoint": { "total": 0.08919615400009206, "count": 1, "self": 0.08919615400009206 } } } } } } }