{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7711260318756104, "min": 0.7711260318756104, "max": 2.8463387489318848, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7897.1015625, "min": 7897.1015625, "max": 29243.28515625, "count": 19 }, "SnowballTarget.Step.mean": { "value": 189968.0, "min": 9952.0, "max": 189968.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 189968.0, "min": 9952.0, "max": 189968.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.74492359161377, "min": 0.33420971035957336, "max": 12.74492359161377, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2599.96435546875, "min": 64.83668518066406, "max": 2599.96435546875, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 19 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06840070962703869, "min": 0.06237388737385581, "max": 0.07476198714598556, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.34200354813519346, "min": 0.25408044284809944, "max": 0.3738099357299278, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20708159848171123, "min": 0.13014003701905225, "max": 0.26397596314257266, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.0354079924085562, "min": 0.520560148076209, "max": 1.2494344346079171, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.349570901052628e-06, "min": 8.349570901052628e-06, "max": 0.0002914547396905263, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 4.174785450526314e-05, "min": 4.174785450526314e-05, "max": 0.0013791158297684208, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10278315789473687, "min": 0.10278315789473687, "max": 0.1971515789473684, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5139157894736843, "min": 0.43197473684210524, "max": 0.9597052631578948, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00014887957894736838, "min": 0.00014887957894736838, "max": 0.004857863789473685, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.000744397894736842, "min": 0.000744397894736842, "max": 0.022989292631578947, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.69090909090909, "min": 3.909090909090909, "max": 25.69090909090909, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1413.0, "min": 172.0, "max": 1413.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.69090909090909, "min": 3.909090909090909, "max": 25.69090909090909, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1413.0, "min": 172.0, "max": 1413.0, "count": 19 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 19 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680890800", "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=SnowballTarget3 --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": "1680891222" }, "total": 422.3319283589999, "count": 1, "self": 0.3859073039998293, "children": { "run_training.setup": { "total": 0.1073829490001117, "count": 1, "self": 0.1073829490001117 }, "TrainerController.start_learning": { "total": 421.83863810599996, "count": 1, "self": 0.5487683140186164, "children": { "TrainerController._reset_env": { "total": 3.896041781999884, "count": 1, "self": 3.896041781999884 }, "TrainerController.advance": { "total": 417.2575078329817, "count": 17329, "self": 0.256938664966583, "children": { "env_step": { "total": 417.0005691680151, "count": 17329, "self": 307.2823922409905, "children": { "SubprocessEnvManager._take_step": { "total": 109.46675004100484, "count": 17329, "self": 1.6189397340176583, "children": { "TorchPolicy.evaluate": { "total": 107.84781030698718, "count": 17329, "self": 107.84781030698718 } } }, "workers": { "total": 0.2514268860197717, "count": 17329, "self": 0.0, "children": { "worker_root": { "total": 420.56424154200886, "count": 17329, "is_parallel": true, "self": 195.5184994720139, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053264040000158275, "count": 1, "is_parallel": true, "self": 0.003850777000252492, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014756269997633353, "count": 10, "is_parallel": true, "self": 0.0014756269997633353 } } }, "UnityEnvironment.step": { "total": 0.033580747999849336, "count": 1, "is_parallel": true, "self": 0.000573038999846176, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00030575400000998343, "count": 1, "is_parallel": true, "self": 0.00030575400000998343 }, "communicator.exchange": { "total": 0.030850783999994746, "count": 1, "is_parallel": true, "self": 0.030850783999994746 }, "steps_from_proto": { "total": 0.0018511709999984305, "count": 1, "is_parallel": true, "self": 0.0004283069999928557, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014228640000055748, "count": 10, "is_parallel": true, "self": 0.0014228640000055748 } } } } } } }, "UnityEnvironment.step": { "total": 225.04574206999496, "count": 17328, "is_parallel": true, "self": 9.104779304038857, "children": { "UnityEnvironment._generate_step_input": { "total": 4.939293619988803, "count": 17328, "is_parallel": true, "self": 4.939293619988803 }, "communicator.exchange": { "total": 182.2120260629772, "count": 17328, "is_parallel": true, "self": 182.2120260629772 }, "steps_from_proto": { "total": 28.789643082990096, "count": 17328, "is_parallel": true, "self": 5.552118511010349, "children": { "_process_rank_one_or_two_observation": { "total": 23.237524571979748, "count": 173280, "is_parallel": true, "self": 23.237524571979748 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0005566709999129671, "count": 1, "self": 0.0005566709999129671, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 414.30182287499065, "count": 368290, "is_parallel": true, "self": 8.654256459938097, "children": { "process_trajectory": { "total": 227.8329715550517, "count": 368290, "is_parallel": true, "self": 227.3122707670516, "children": { "RLTrainer._checkpoint": { "total": 0.5207007880001129, "count": 3, "is_parallel": true, "self": 0.5207007880001129 } } }, "_update_policy": { "total": 177.81459486000085, "count": 86, "is_parallel": true, "self": 68.7688658659888, "children": { "TorchPPOOptimizer.update": { "total": 109.04572899401205, "count": 4383, "is_parallel": true, "self": 109.04572899401205 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13576350599987563, "count": 1, "self": 0.0009187050000036834, "children": { "RLTrainer._checkpoint": { "total": 0.13484480099987195, "count": 1, "self": 0.13484480099987195 } } } } } } }