{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8867369890213013, "min": 0.8867369890213013, "max": 2.8655693531036377, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8505.5810546875, "min": 8505.5810546875, "max": 29409.337890625, "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": 13.046875, "min": 0.492266982793808, "max": 13.046875, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2544.140625, "min": 95.49979400634766, "max": 2648.087890625, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.05997834385397807, "min": 0.05997834385397807, "max": 0.07576822043851923, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2399133754159123, "min": 0.2399133754159123, "max": 0.37884110219259615, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.20376944804892821, "min": 0.12399268490901472, "max": 0.2859430268114688, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8150777921957129, "min": 0.49597073963605887, "max": 1.4297151340573442, "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": 25.772727272727273, "min": 4.204545454545454, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1134.0, "min": 185.0, "max": 1411.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.772727272727273, "min": 4.204545454545454, "max": 25.90909090909091, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1134.0, "min": 185.0, "max": 1411.0, "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": "1686583119", "python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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=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": "1686583698" }, "total": 578.381406132, "count": 1, "self": 0.9531930520000742, "children": { "run_training.setup": { "total": 0.07172308900004509, "count": 1, "self": 0.07172308900004509 }, "TrainerController.start_learning": { "total": 577.356489991, "count": 1, "self": 0.7381638260003456, "children": { "TrainerController._reset_env": { "total": 5.815364906000013, "count": 1, "self": 5.815364906000013 }, "TrainerController.advance": { "total": 570.5417217109995, "count": 18230, "self": 0.38011827400202947, "children": { "env_step": { "total": 570.1616034369974, "count": 18230, "self": 415.2228667380073, "children": { "SubprocessEnvManager._take_step": { "total": 154.57025875799974, "count": 18230, "self": 2.329320297002539, "children": { "TorchPolicy.evaluate": { "total": 152.2409384609972, "count": 18230, "self": 152.2409384609972 } } }, "workers": { "total": 0.368477940990374, "count": 18230, "self": 0.0, "children": { "worker_root": { "total": 574.9013252950081, "count": 18230, "is_parallel": true, "self": 264.8934394190214, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.006853279999972983, "count": 1, "is_parallel": true, "self": 0.004323302999978296, "children": { "_process_rank_one_or_two_observation": { "total": 0.0025299769999946875, "count": 10, "is_parallel": true, "self": 0.0025299769999946875 } } }, "UnityEnvironment.step": { "total": 0.03998278200003824, "count": 1, "is_parallel": true, "self": 0.0006589900000335547, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00029402000001255146, "count": 1, "is_parallel": true, "self": 0.00029402000001255146 }, "communicator.exchange": { "total": 0.0366775109999935, "count": 1, "is_parallel": true, "self": 0.0366775109999935 }, "steps_from_proto": { "total": 0.0023522609999986344, "count": 1, "is_parallel": true, "self": 0.0004488470000296729, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019034139999689614, "count": 10, "is_parallel": true, "self": 0.0019034139999689614 } } } } } } }, "UnityEnvironment.step": { "total": 310.0078858759867, "count": 18229, "is_parallel": true, "self": 12.6898613589849, "children": { "UnityEnvironment._generate_step_input": { "total": 6.402676535993692, "count": 18229, "is_parallel": true, "self": 6.402676535993692 }, "communicator.exchange": { "total": 248.24702683600935, "count": 18229, "is_parallel": true, "self": 248.24702683600935 }, "steps_from_proto": { "total": 42.66832114499874, "count": 18229, "is_parallel": true, "self": 8.275188611003898, "children": { "_process_rank_one_or_two_observation": { "total": 34.393132533994844, "count": 182290, "is_parallel": true, "self": 34.393132533994844 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0001654920000646598, "count": 1, "self": 0.0001654920000646598, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 565.8226938610748, "count": 546312, "is_parallel": true, "self": 12.58049569512616, "children": { "process_trajectory": { "total": 320.60923400694793, "count": 546312, "is_parallel": true, "self": 305.64768057594847, "children": { "RLTrainer._checkpoint": { "total": 14.961553430999459, "count": 40, "is_parallel": true, "self": 14.961553430999459 } } }, "_update_policy": { "total": 232.63296415900066, "count": 90, "is_parallel": true, "self": 86.53489770399852, "children": { "TorchPPOOptimizer.update": { "total": 146.09806645500214, "count": 4587, "is_parallel": true, "self": 146.09806645500214 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2610740560000977, "count": 1, "self": 0.003333339000050728, "children": { "RLTrainer._checkpoint": { "total": 0.25774071700004697, "count": 1, "self": 0.25774071700004697 } } } } } } }