{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9464752078056335, "min": 0.9464752078056335, "max": 2.856548309326172, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9036.9453125, "min": 9036.9453125, "max": 29411.021484375, "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": 12.40365219116211, "min": 0.4493948519229889, "max": 12.40365219116211, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2418.712158203125, "min": 87.18260192871094, "max": 2499.390625, "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": 0.06935380795067769, "min": 0.06116668480464404, "max": 0.07979653622252027, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.27741523180271077, "min": 0.24466673921857615, "max": 0.3989826811126013, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18440675731821388, "min": 0.1367649126754544, "max": 0.2963413303973628, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7376270292728555, "min": 0.5470596507018176, "max": 1.4180577654464572, "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": 25.09090909090909, "min": 3.5454545454545454, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1104.0, "min": 156.0, "max": 1346.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.09090909090909, "min": 3.5454545454545454, "max": 25.09090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1104.0, "min": 156.0, "max": 1346.0, "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": "1680099286", "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": "1680099793" }, "total": 506.971046593, "count": 1, "self": 0.4296502939998845, "children": { "run_training.setup": { "total": 0.12730788199996823, "count": 1, "self": 0.12730788199996823 }, "TrainerController.start_learning": { "total": 506.41408841700013, "count": 1, "self": 0.6159046570271585, "children": { "TrainerController._reset_env": { "total": 9.720733872999972, "count": 1, "self": 9.720733872999972 }, "TrainerController.advance": { "total": 495.924885585973, "count": 18201, "self": 0.32111787695089333, "children": { "env_step": { "total": 495.6037677090221, "count": 18201, "self": 358.8907081360112, "children": { "SubprocessEnvManager._take_step": { "total": 136.40654953301305, "count": 18201, "self": 2.3049257430068337, "children": { "TorchPolicy.evaluate": { "total": 134.10162379000622, "count": 18201, "self": 134.10162379000622 } } }, "workers": { "total": 0.30651003999787463, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 504.7610100870247, "count": 18201, "is_parallel": true, "self": 237.94302542403352, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006321192000086739, "count": 1, "is_parallel": true, "self": 0.004695948000517092, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016252439995696477, "count": 10, "is_parallel": true, "self": 0.0016252439995696477 } } }, "UnityEnvironment.step": { "total": 0.04304432800017821, "count": 1, "is_parallel": true, "self": 0.0005303440002535353, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003334900000027119, "count": 1, "is_parallel": true, "self": 0.0003334900000027119 }, "communicator.exchange": { "total": 0.04025499299996227, "count": 1, "is_parallel": true, "self": 0.04025499299996227 }, "steps_from_proto": { "total": 0.001925500999959695, "count": 1, "is_parallel": true, "self": 0.0003896400000940048, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015358609998656902, "count": 10, "is_parallel": true, "self": 0.0015358609998656902 } } } } } } }, "UnityEnvironment.step": { "total": 266.8179846629912, "count": 18200, "is_parallel": true, "self": 10.13031641505495, "children": { "UnityEnvironment._generate_step_input": { "total": 5.772272080972471, "count": 18200, "is_parallel": true, "self": 5.772272080972471 }, "communicator.exchange": { "total": 215.48698379398706, "count": 18200, "is_parallel": true, "self": 215.48698379398706 }, "steps_from_proto": { "total": 35.42841237297671, "count": 18200, "is_parallel": true, "self": 7.274889485963058, "children": { "_process_rank_one_or_two_observation": { "total": 28.15352288701365, "count": 182000, "is_parallel": true, "self": 28.15352288701365 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.000163091000104032, "count": 1, "self": 0.000163091000104032, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 492.1753861760467, "count": 440097, "is_parallel": true, "self": 11.084077535028882, "children": { "process_trajectory": { "total": 273.395698493018, "count": 440097, "is_parallel": true, "self": 272.60421044101827, "children": { "RLTrainer._checkpoint": { "total": 0.7914880519997496, "count": 4, "is_parallel": true, "self": 0.7914880519997496 } } }, "_update_policy": { "total": 207.6956101479998, "count": 90, "is_parallel": true, "self": 76.08158776201117, "children": { "TorchPPOOptimizer.update": { "total": 131.61402238598862, "count": 4587, "is_parallel": true, "self": 131.61402238598862 } } } } } } } } }, "TrainerController._save_models": { "total": 0.15240120999987994, "count": 1, "self": 0.000979893999556225, "children": { "RLTrainer._checkpoint": { "total": 0.1514213160003237, "count": 1, "self": 0.1514213160003237 } } } } } } }