{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9027432203292847, "min": 0.8886774182319641, "max": 2.865996837615967, "count": 25 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8589.6015625, "min": 8465.541015625, "max": 29413.724609375, "count": 25 }, "SnowballTarget.Step.mean": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Step.sum": { "value": 249944.0, "min": 9952.0, "max": 249944.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.0246000289917, "min": 0.3905719518661499, "max": 13.030131340026855, "count": 25 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.7724609375, "min": 75.77095794677734, "max": 2671.177001953125, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 25 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.0660443901213904, "min": 0.0623700422681092, "max": 0.073655227968451, "count": 25 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2641775604855616, "min": 0.2494801690724368, "max": 0.368276139842255, "count": 25 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18798936282594997, "min": 0.14285855851930512, "max": 0.28174183466563035, "count": 25 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7519574513037999, "min": 0.5714342340772205, "max": 1.3732448193956823, "count": 25 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.7456980848e-06, "min": 5.7456980848e-06, "max": 0.0002935056021648, "count": 25 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.29827923392e-05, "min": 2.29827923392e-05, "max": 0.0014081280306239997, "count": 25 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10191520000000001, "min": 0.10191520000000001, "max": 0.19783520000000002, "count": 25 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.40766080000000005, "min": 0.40766080000000005, "max": 0.9693760000000002, "count": 25 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00010556848000000002, "min": 0.00010556848000000002, "max": 0.004891976480000001, "count": 25 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004222739200000001, "min": 0.0004222739200000001, "max": 0.023471862399999998, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.90909090909091, "min": 3.3863636363636362, "max": 26.022222222222222, "count": 25 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1140.0, "min": 149.0, "max": 1417.0, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.90909090909091, "min": 3.3863636363636362, "max": 26.022222222222222, "count": 25 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1140.0, "min": 149.0, "max": 1417.0, "count": 25 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 25 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1680965607", "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=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": "1680966180" }, "total": 573.625759773, "count": 1, "self": 0.7449315029998616, "children": { "run_training.setup": { "total": 0.11715758700006518, "count": 1, "self": 0.11715758700006518 }, "TrainerController.start_learning": { "total": 572.7636706830001, "count": 1, "self": 0.6902432800093266, "children": { "TrainerController._reset_env": { "total": 4.731449273999942, "count": 1, "self": 4.731449273999942 }, "TrainerController.advance": { "total": 567.1304799789905, "count": 22739, "self": 0.3552740759826065, "children": { "env_step": { "total": 566.7752059030079, "count": 22739, "self": 417.0431853780324, "children": { "SubprocessEnvManager._take_step": { "total": 149.39359234996095, "count": 22739, "self": 2.057052624943708, "children": { "TorchPolicy.evaluate": { "total": 147.33653972501725, "count": 22739, "self": 147.33653972501725 } } }, "workers": { "total": 0.3384281750145419, "count": 22739, "self": 0.0, "children": { "worker_root": { "total": 571.0822307699516, "count": 22739, "is_parallel": true, "self": 263.0863309479471, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00551649399994858, "count": 1, "is_parallel": true, "self": 0.0039796349999505765, "children": { "_process_rank_one_or_two_observation": { "total": 0.0015368589999980031, "count": 10, "is_parallel": true, "self": 0.0015368589999980031 } } }, "UnityEnvironment.step": { "total": 0.05870996599992395, "count": 1, "is_parallel": true, "self": 0.0005982010000025184, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00036842999998043524, "count": 1, "is_parallel": true, "self": 0.00036842999998043524 }, "communicator.exchange": { "total": 0.05605310000009922, "count": 1, "is_parallel": true, "self": 0.05605310000009922 }, "steps_from_proto": { "total": 0.0016902349998417776, "count": 1, "is_parallel": true, "self": 0.0003575609998733853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013326739999683923, "count": 10, "is_parallel": true, "self": 0.0013326739999683923 } } } } } } }, "UnityEnvironment.step": { "total": 307.9958998220045, "count": 22738, "is_parallel": true, "self": 12.339288863027377, "children": { "UnityEnvironment._generate_step_input": { "total": 6.677939529005016, "count": 22738, "is_parallel": true, "self": 6.677939529005016 }, "communicator.exchange": { "total": 249.75194673997976, "count": 22738, "is_parallel": true, "self": 249.75194673997976 }, "steps_from_proto": { "total": 39.22672468999235, "count": 22738, "is_parallel": true, "self": 7.7075016479846, "children": { "_process_rank_one_or_two_observation": { "total": 31.519223042007752, "count": 227380, "is_parallel": true, "self": 31.519223042007752 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.2509000144928e-05, "count": 1, "self": 6.2509000144928e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 563.0555842489307, "count": 499853, "is_parallel": true, "self": 11.804565787029787, "children": { "process_trajectory": { "total": 308.9915419829015, "count": 499853, "is_parallel": true, "self": 308.04244291990176, "children": { "RLTrainer._checkpoint": { "total": 0.9490990629997214, "count": 5, "is_parallel": true, "self": 0.9490990629997214 } } }, "_update_policy": { "total": 242.25947647899943, "count": 113, "is_parallel": true, "self": 92.56769424300501, "children": { "TorchPPOOptimizer.update": { "total": 149.69178223599442, "count": 5760, "is_parallel": true, "self": 149.69178223599442 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2114356410002074, "count": 1, "self": 0.0011193720001756446, "children": { "RLTrainer._checkpoint": { "total": 0.21031626900003175, "count": 1, "self": 0.21031626900003175 } } } } } } }