{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8884783387184143, "min": 0.8884783387184143, "max": 2.849780797958374, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8483.19140625, "min": 8483.19140625, "max": 29184.60546875, "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": 12.989903450012207, "min": 0.37545090913772583, "max": 12.989903450012207, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2533.03125, "min": 72.83747863769531, "max": 2597.1103515625, "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": 0.06527416815472808, "min": 0.06048949091471549, "max": 0.07682839385667524, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26109667261891234, "min": 0.24195796365886196, "max": 0.3841419692833762, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1863940691246706, "min": 0.11732079479934684, "max": 0.28565019734349906, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7455762764986824, "min": 0.4692831791973874, "max": 1.2943979498802447, "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": 25.954545454545453, "min": 3.5, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1142.0, "min": 154.0, "max": 1397.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.954545454545453, "min": 3.5, "max": 25.954545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1142.0, "min": 154.0, "max": 1397.0, "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": "1673720122", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1673720551" }, "total": 429.75244040399997, "count": 1, "self": 0.38686400099993534, "children": { "run_training.setup": { "total": 0.11139505599999211, "count": 1, "self": 0.11139505599999211 }, "TrainerController.start_learning": { "total": 429.25418134700004, "count": 1, "self": 0.4954371450004942, "children": { "TrainerController._reset_env": { "total": 9.707492054999989, "count": 1, "self": 9.707492054999989 }, "TrainerController.advance": { "total": 418.92789516399955, "count": 18201, "self": 0.26162188399797515, "children": { "env_step": { "total": 418.6662732800016, "count": 18201, "self": 269.7923324310117, "children": { "SubprocessEnvManager._take_step": { "total": 148.61909513699436, "count": 18201, "self": 1.387872315992297, "children": { "TorchPolicy.evaluate": { "total": 147.23122282100206, "count": 18201, "self": 32.861783471000535, "children": { "TorchPolicy.sample_actions": { "total": 114.36943935000153, "count": 18201, "self": 114.36943935000153 } } } } }, "workers": { "total": 0.25484571199552875, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 428.0855313329976, "count": 18201, "is_parallel": true, "self": 210.5125753940082, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.007132248999994317, "count": 1, "is_parallel": true, "self": 0.004439195000031759, "children": { "_process_rank_one_or_two_observation": { "total": 0.002693053999962558, "count": 10, "is_parallel": true, "self": 0.002693053999962558 } } }, "UnityEnvironment.step": { "total": 0.03336573199999293, "count": 1, "is_parallel": true, "self": 0.0004992090000541793, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00028247999995301143, "count": 1, "is_parallel": true, "self": 0.00028247999995301143 }, "communicator.exchange": { "total": 0.03062342999999146, "count": 1, "is_parallel": true, "self": 0.03062342999999146 }, "steps_from_proto": { "total": 0.0019606129999942823, "count": 1, "is_parallel": true, "self": 0.0005194610000103239, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014411519999839584, "count": 10, "is_parallel": true, "self": 0.0014411519999839584 } } } } } } }, "UnityEnvironment.step": { "total": 217.57295593898942, "count": 18200, "is_parallel": true, "self": 8.435502254976711, "children": { "UnityEnvironment._generate_step_input": { "total": 4.914650953006742, "count": 18200, "is_parallel": true, "self": 4.914650953006742 }, "communicator.exchange": { "total": 174.10087315900228, "count": 18200, "is_parallel": true, "self": 174.10087315900228 }, "steps_from_proto": { "total": 30.121929572003694, "count": 18200, "is_parallel": true, "self": 6.347514773027058, "children": { "_process_rank_one_or_two_observation": { "total": 23.774414798976636, "count": 182000, "is_parallel": true, "self": 23.774414798976636 } } } } } } } } } } } } }, "trainer_threads": { "total": 4.351799998403294e-05, "count": 1, "self": 4.351799998403294e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 416.0495020149841, "count": 334856, "is_parallel": true, "self": 9.013341660983258, "children": { "process_trajectory": { "total": 237.44090808900233, "count": 334856, "is_parallel": true, "self": 236.66557931700237, "children": { "RLTrainer._checkpoint": { "total": 0.7753287719999662, "count": 4, "is_parallel": true, "self": 0.7753287719999662 } } }, "_update_policy": { "total": 169.59525226499852, "count": 90, "is_parallel": true, "self": 45.05092604499788, "children": { "TorchPPOOptimizer.update": { "total": 124.54432622000064, "count": 4587, "is_parallel": true, "self": 124.54432622000064 } } } } } } } } }, "TrainerController._save_models": { "total": 0.12331346500002383, "count": 1, "self": 0.0008297699999957331, "children": { "RLTrainer._checkpoint": { "total": 0.12248369500002809, "count": 1, "self": 0.12248369500002809 } } } } } } }