{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8581987619400024, "min": 0.8581987619400024, "max": 2.8765792846679688, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8194.08203125, "min": 8194.08203125, "max": 29427.40625, "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": 13.107649803161621, "min": 0.19389332830905914, "max": 13.107649803161621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2555.99169921875, "min": 37.61530685424805, "max": 2656.22802734375, "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": 0.06708384718256317, "min": 0.061779246055212914, "max": 0.0752643468571763, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2683353887302527, "min": 0.24711698422085165, "max": 0.373156489823219, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18201275509508216, "min": 0.08840154117091979, "max": 0.2925294505030501, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7280510203803287, "min": 0.35360616468367917, "max": 1.4626472525152505, "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": 2.75, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1143.0, "min": 121.0, "max": 1408.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.977272727272727, "min": 2.75, "max": 25.977272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1143.0, "min": 121.0, "max": 1408.0, "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": "1677595001", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=SnowballTarget2 --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": "1.22.4", "end_time_seconds": "1677595460" }, "total": 459.62222407599995, "count": 1, "self": 0.3879432909999423, "children": { "run_training.setup": { "total": 0.10838640400001509, "count": 1, "self": 0.10838640400001509 }, "TrainerController.start_learning": { "total": 459.12589438099997, "count": 1, "self": 0.5840100640047581, "children": { "TrainerController._reset_env": { "total": 9.835260661999996, "count": 1, "self": 9.835260661999996 }, "TrainerController.advance": { "total": 448.5892630929953, "count": 18203, "self": 0.2957110049915741, "children": { "env_step": { "total": 448.2935520880037, "count": 18203, "self": 308.87407783500754, "children": { "SubprocessEnvManager._take_step": { "total": 139.12717441899645, "count": 18203, "self": 1.5227019069970993, "children": { "TorchPolicy.evaluate": { "total": 137.60447251199935, "count": 18203, "self": 32.27377044499892, "children": { "TorchPolicy.sample_actions": { "total": 105.33070206700043, "count": 18203, "self": 105.33070206700043 } } } } }, "workers": { "total": 0.2922998339997207, "count": 18203, "self": 0.0, "children": { "worker_root": { "total": 457.4372354229988, "count": 18203, "is_parallel": true, "self": 219.51095323699886, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004898515999997244, "count": 1, "is_parallel": true, "self": 0.0035690129999750297, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013295030000222141, "count": 10, "is_parallel": true, "self": 0.0013295030000222141 } } }, "UnityEnvironment.step": { "total": 0.03286983199998872, "count": 1, "is_parallel": true, "self": 0.000578763000021354, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002975579999997535, "count": 1, "is_parallel": true, "self": 0.0002975579999997535 }, "communicator.exchange": { "total": 0.030274951999984978, "count": 1, "is_parallel": true, "self": 0.030274951999984978 }, "steps_from_proto": { "total": 0.0017185589999826334, "count": 1, "is_parallel": true, "self": 0.0004030150001028687, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013155439998797647, "count": 10, "is_parallel": true, "self": 0.0013155439998797647 } } } } } } }, "UnityEnvironment.step": { "total": 237.92628218599995, "count": 18202, "is_parallel": true, "self": 9.623949214987476, "children": { "UnityEnvironment._generate_step_input": { "total": 5.174563551004269, "count": 18202, "is_parallel": true, "self": 5.174563551004269 }, "communicator.exchange": { "total": 192.53865922800503, "count": 18202, "is_parallel": true, "self": 192.53865922800503 }, "steps_from_proto": { "total": 30.589110192003176, "count": 18202, "is_parallel": true, "self": 6.873278269995325, "children": { "_process_rank_one_or_two_observation": { "total": 23.71583192200785, "count": 182020, "is_parallel": true, "self": 23.71583192200785 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001477739999700134, "count": 1, "self": 0.0001477739999700134, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 445.3573258009915, "count": 402442, "is_parallel": true, "self": 9.803518441968095, "children": { "process_trajectory": { "total": 256.92977332102333, "count": 402442, "is_parallel": true, "self": 256.2195990470233, "children": { "RLTrainer._checkpoint": { "total": 0.7101742740000532, "count": 4, "is_parallel": true, "self": 0.7101742740000532 } } }, "_update_policy": { "total": 178.62403403800008, "count": 90, "is_parallel": true, "self": 61.23756033500007, "children": { "TorchPPOOptimizer.update": { "total": 117.38647370300001, "count": 4587, "is_parallel": true, "self": 117.38647370300001 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11721278799996071, "count": 1, "self": 0.0008760989999245794, "children": { "RLTrainer._checkpoint": { "total": 0.11633668900003613, "count": 1, "self": 0.11633668900003613 } } } } } } }