{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9889045357704163, "min": 0.9889045357704163, "max": 2.871359348297119, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9442.060546875, "min": 9442.060546875, "max": 29468.76171875, "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": 12.983160972595215, "min": 0.4284287989139557, "max": 12.983160972595215, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2531.71630859375, "min": 83.11518859863281, "max": 2634.013916015625, "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": 0.06351111452742914, "min": 0.06351111452742914, "max": 0.07683608270808712, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25404445810971654, "min": 0.25404445810971654, "max": 0.3806481976929468, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2372759584994877, "min": 0.12119883984582974, "max": 0.2808480512277753, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.9491038339979508, "min": 0.48479535938331897, "max": 1.4042402561388765, "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": 25.454545454545453, "min": 3.4545454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 152.0, "max": 1407.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.4545454545454546, "max": 25.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 152.0, "max": 1407.0, "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": "1680115864", "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 /content/ml-agents/config/ppo/SnowballTarget.yaml --env=/content/ml-agents/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": "1680116321" }, "total": 457.495102729, "count": 1, "self": 0.4349114130000089, "children": { "run_training.setup": { "total": 0.17591178399999308, "count": 1, "self": 0.17591178399999308 }, "TrainerController.start_learning": { "total": 456.884279532, "count": 1, "self": 0.534772755003587, "children": { "TrainerController._reset_env": { "total": 9.014268765999986, "count": 1, "self": 9.014268765999986 }, "TrainerController.advance": { "total": 447.1941745019963, "count": 18201, "self": 0.2634565800020141, "children": { "env_step": { "total": 446.9307179219943, "count": 18201, "self": 325.3246911039849, "children": { "SubprocessEnvManager._take_step": { "total": 121.34443236600521, "count": 18201, "self": 2.522684289014421, "children": { "TorchPolicy.evaluate": { "total": 118.82174807699079, "count": 18201, "self": 118.82174807699079 } } }, "workers": { "total": 0.2615944520042035, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 455.58282562099555, "count": 18201, "is_parallel": true, "self": 220.91168144799627, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005607442000041374, "count": 1, "is_parallel": true, "self": 0.004083589000117627, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015238529999237471, "count": 10, "is_parallel": true, "self": 0.0015238529999237471 } } }, "UnityEnvironment.step": { "total": 0.034363370999983545, "count": 1, "is_parallel": true, "self": 0.0003920710000215877, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00032147999996823273, "count": 1, "is_parallel": true, "self": 0.00032147999996823273 }, "communicator.exchange": { "total": 0.0321322949999967, "count": 1, "is_parallel": true, "self": 0.0321322949999967 }, "steps_from_proto": { "total": 0.001517524999997022, "count": 1, "is_parallel": true, "self": 0.0003642629999944802, "children": { "_process_rank_one_or_two_observation": { "total": 0.0011532620000025418, "count": 10, "is_parallel": true, "self": 0.0011532620000025418 } } } } } } }, "UnityEnvironment.step": { "total": 234.67114417299928, "count": 18200, "is_parallel": true, "self": 9.369571812002619, "children": { "UnityEnvironment._generate_step_input": { "total": 5.144679942993946, "count": 18200, "is_parallel": true, "self": 5.144679942993946 }, "communicator.exchange": { "total": 189.96652086000012, "count": 18200, "is_parallel": true, "self": 189.96652086000012 }, "steps_from_proto": { "total": 30.190371558002596, "count": 18200, "is_parallel": true, "self": 5.8808508379950695, "children": { "_process_rank_one_or_two_observation": { "total": 24.309520720007527, "count": 182000, "is_parallel": true, "self": 24.309520720007527 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00012944000002335088, "count": 1, "self": 0.00012944000002335088, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 443.9281739550023, "count": 387115, "is_parallel": true, "self": 9.677141758019332, "children": { "process_trajectory": { "total": 244.27273216298323, "count": 387115, "is_parallel": true, "self": 243.45115495498322, "children": { "RLTrainer._checkpoint": { "total": 0.8215772080000079, "count": 4, "is_parallel": true, "self": 0.8215772080000079 } } }, "_update_policy": { "total": 189.97830003399974, "count": 90, "is_parallel": true, "self": 73.512982455003, "children": { "TorchPPOOptimizer.update": { "total": 116.46531757899675, "count": 4587, "is_parallel": true, "self": 116.46531757899675 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14093406900008176, "count": 1, "self": 0.0009035940000785558, "children": { "RLTrainer._checkpoint": { "total": 0.1400304750000032, "count": 1, "self": 0.1400304750000032 } } } } } } }