{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.0305557250976562, "min": 1.0305557250976562, "max": 2.6767399311065674, "count": 19 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9873.75390625, "min": 9873.75390625, "max": 25146.279296875, "count": 19 }, "SnowballTarget.Step.mean": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Step.sum": { "value": 199960.0, "min": 19968.0, "max": 199960.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.28280258178711, "min": 1.582127332687378, "max": 12.28280258178711, "count": 19 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2395.146484375, "min": 215.1693115234375, "max": 2456.0576171875, "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": 6567.0, "max": 10945.0, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07153849720534887, "min": 0.0650355018891894, "max": 0.07437872416180029, "count": 19 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2861539888213955, "min": 0.20904549251695154, "max": 0.37189362080900146, "count": 19 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.21812057013020794, "min": 0.18783810018908745, "max": 0.26509962274747734, "count": 19 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8724822805208318, "min": 0.5861201091833851, "max": 1.299587918847215, "count": 19 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.214097262000005e-06, "min": 8.214097262000005e-06, "max": 0.000273864008712, "count": 19 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.285638904800002e-05, "min": 3.285638904800002e-05, "max": 0.00123732008756, "count": 19 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10273800000000001, "min": 0.10273800000000001, "max": 0.19128799999999999, "count": 19 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41095200000000004, "min": 0.41095200000000004, "max": 0.9124400000000001, "count": 19 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001466262000000001, "min": 0.0001466262000000001, "max": 0.004565271199999999, "count": 19 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005865048000000004, "min": 0.0005865048000000004, "max": 0.020630756, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 24.568181818181817, "min": 6.393939393939394, "max": 24.78181818181818, "count": 19 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1081.0, "min": 211.0, "max": 1363.0, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 24.568181818181817, "min": 6.393939393939394, "max": 24.78181818181818, "count": 19 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1081.0, "min": 211.0, "max": 1363.0, "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": "1682472564", "python_version": "3.9.16 (main, Apr 26 2023, 09:57:11) \n[GCC 9.4.0]", "command_line_arguments": "/home/isaac/python_envs/py3916_env/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume", "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": "1682472779" }, "total": 215.00497559900396, "count": 1, "self": 0.2196071700018365, "children": { "run_training.setup": { "total": 0.03277779099880718, "count": 1, "self": 0.03277779099880718 }, "TrainerController.start_learning": { "total": 214.7525906380033, "count": 1, "self": 0.347331655677408, "children": { "TrainerController._reset_env": { "total": 2.209427320995019, "count": 1, "self": 2.209427320995019 }, "TrainerController.advance": { "total": 212.10186213132693, "count": 17004, "self": 0.17319778741511982, "children": { "env_step": { "total": 211.9286643439118, "count": 17004, "self": 149.39888549630996, "children": { "SubprocessEnvManager._take_step": { "total": 62.354847080874606, "count": 17004, "self": 0.8606052966497373, "children": { "TorchPolicy.evaluate": { "total": 61.49424178422487, "count": 17004, "self": 61.49424178422487 } } }, "workers": { "total": 0.17493176672724076, "count": 17004, "self": 0.0, "children": { "worker_root": { "total": 214.34768923617958, "count": 17004, "is_parallel": true, "self": 123.48211874165281, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010480040073161945, "count": 1, "is_parallel": true, "self": 0.0002753550070337951, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007726490002823994, "count": 10, "is_parallel": true, "self": 0.0007726490002823994 } } }, "UnityEnvironment.step": { "total": 0.015450181002961472, "count": 1, "is_parallel": true, "self": 0.00021916399418842047, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00017331501294393092, "count": 1, "is_parallel": true, "self": 0.00017331501294393092 }, "communicator.exchange": { "total": 0.014249605999793857, "count": 1, "is_parallel": true, "self": 0.014249605999793857 }, "steps_from_proto": { "total": 0.0008080959960352629, "count": 1, "is_parallel": true, "self": 0.00019075500313192606, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006173409929033369, "count": 10, "is_parallel": true, "self": 0.0006173409929033369 } } } } } } }, "UnityEnvironment.step": { "total": 90.86557049452676, "count": 17003, "is_parallel": true, "self": 3.9357192841998767, "children": { "UnityEnvironment._generate_step_input": { "total": 2.594641712945304, "count": 17003, "is_parallel": true, "self": 2.594641712945304 }, "communicator.exchange": { "total": 70.02356578952458, "count": 17003, "is_parallel": true, "self": 70.02356578952458 }, "steps_from_proto": { "total": 14.311643707857002, "count": 17003, "is_parallel": true, "self": 3.254882780223852, "children": { "_process_rank_one_or_two_observation": { "total": 11.05676092763315, "count": 170030, "is_parallel": true, "self": 11.05676092763315 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.265900447033346e-05, "count": 1, "self": 6.265900447033346e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 211.82577092766587, "count": 127653, "is_parallel": true, "self": 1.4739056372345658, "children": { "process_trajectory": { "total": 111.39946549842716, "count": 127653, "is_parallel": true, "self": 110.85940189742541, "children": { "RLTrainer._checkpoint": { "total": 0.5400636010017479, "count": 4, "is_parallel": true, "self": 0.5400636010017479 } } }, "_update_policy": { "total": 98.95239979200414, "count": 84, "is_parallel": true, "self": 32.9943716678099, "children": { "TorchPPOOptimizer.update": { "total": 65.95802812419424, "count": 4281, "is_parallel": true, "self": 65.95802812419424 } } } } } } } } }, "TrainerController._save_models": { "total": 0.09390687099948991, "count": 1, "self": 0.0005450370081234723, "children": { "RLTrainer._checkpoint": { "total": 0.09336183399136644, "count": 1, "self": 0.09336183399136644 } } } } } } }