{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.763594150543213, "min": 2.763594150543213, "max": 2.8903441429138184, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6140.7060546875, "min": 4374.513671875, "max": 6305.4208984375, "count": 10 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 1984.0, "max": 19992.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 1984.0, "max": 19992.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 1.773027777671814, "min": 0.031246062368154526, "max": 1.773027777671814, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 72.69413757324219, "min": 0.9686279296875, "max": 72.69413757324219, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.08255767953175795, "min": 0.0569285657827505, "max": 0.08255767953175795, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.08255767953175795, "min": 0.0569285657827505, "max": 0.08255767953175795, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24942323331739388, "min": 0.09339500664203775, "max": 0.2606781861361335, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.24942323331739388, "min": 0.09339500664203775, "max": 0.2606781861361335, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.320098559999991e-06, "min": 4.320098559999991e-06, "max": 0.00026832001056, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 6.909090909090909, "min": 2.4545454545454546, "max": 6.909090909090909, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 76.0, "min": 27.0, "max": 76.0, "count": 9 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 6.909090909090909, "min": 2.4545454545454546, "max": 6.909090909090909, "count": 9 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 76.0, "min": 27.0, "max": 76.0, "count": 9 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1687053539", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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": "1687053595" }, "total": 56.221318999999994, "count": 1, "self": 0.43031734599981064, "children": { "run_training.setup": { "total": 0.062232017000042106, "count": 1, "self": 0.062232017000042106 }, "TrainerController.start_learning": { "total": 55.72876963700014, "count": 1, "self": 0.09686754700214806, "children": { "TrainerController._reset_env": { "total": 5.316966488000162, "count": 1, "self": 5.316966488000162 }, "TrainerController.advance": { "total": 50.17691266499787, "count": 1875, "self": 0.033726492996947854, "children": { "env_step": { "total": 50.143186172000924, "count": 1875, "self": 36.62652983499606, "children": { "SubprocessEnvManager._take_step": { "total": 13.485013618002313, "count": 1875, "self": 0.18535533900171686, "children": { "TorchPolicy.evaluate": { "total": 13.299658279000596, "count": 1875, "self": 13.299658279000596 } } }, "workers": { "total": 0.03164271900254789, "count": 1875, "self": 0.0, "children": { "worker_root": { "total": 55.4537239719989, "count": 1875, "is_parallel": true, "self": 28.21760304800341, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00683415799994691, "count": 1, "is_parallel": true, "self": 0.004369390999954703, "children": { "_process_rank_one_or_two_observation": { "total": 0.0024647669999922073, "count": 10, "is_parallel": true, "self": 0.0024647669999922073 } } }, "UnityEnvironment.step": { "total": 0.035569780000059836, "count": 1, "is_parallel": true, "self": 0.0006767090001176257, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00041505800004415505, "count": 1, "is_parallel": true, "self": 0.00041505800004415505 }, "communicator.exchange": { "total": 0.032307062999962, "count": 1, "is_parallel": true, "self": 0.032307062999962 }, "steps_from_proto": { "total": 0.002170949999936056, "count": 1, "is_parallel": true, "self": 0.00043183699995097413, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017391129999850818, "count": 10, "is_parallel": true, "self": 0.0017391129999850818 } } } } } } }, "UnityEnvironment.step": { "total": 27.236120923995486, "count": 1874, "is_parallel": true, "self": 1.150547218993779, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5702390229969296, "count": 1874, "is_parallel": true, "self": 0.5702390229969296 }, "communicator.exchange": { "total": 21.75877514199601, "count": 1874, "is_parallel": true, "self": 21.75877514199601 }, "steps_from_proto": { "total": 3.756559540008766, "count": 1874, "is_parallel": true, "self": 0.6851786480008286, "children": { "_process_rank_one_or_two_observation": { "total": 3.0713808920079373, "count": 18740, "is_parallel": true, "self": 3.0713808920079373 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003016210000623687, "count": 1, "self": 0.0003016210000623687, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 49.86486301100649, "count": 45715, "is_parallel": true, "self": 0.9581825099892285, "children": { "process_trajectory": { "total": 28.008447348016944, "count": 45715, "is_parallel": true, "self": 26.38692417401694, "children": { "RLTrainer._checkpoint": { "total": 1.6215231740000036, "count": 4, "is_parallel": true, "self": 1.6215231740000036 } } }, "_update_policy": { "total": 20.89823315300032, "count": 9, "is_parallel": true, "self": 8.020640838998816, "children": { "TorchPPOOptimizer.update": { "total": 12.877592314001504, "count": 456, "is_parallel": true, "self": 12.877592314001504 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13772131599989734, "count": 1, "self": 0.0008859069998834457, "children": { "RLTrainer._checkpoint": { "total": 0.1368354090000139, "count": 1, "self": 0.1368354090000139 } } } } } } }