{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7605854272842407, "min": 0.7482065558433533, "max": 2.86487078666687, "count": 40 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7722.2236328125, "min": 7277.4931640625, "max": 29370.654296875, "count": 40 }, "SnowballTarget.Step.mean": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Step.sum": { "value": 399992.0, "min": 9952.0, "max": 399992.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.41388988494873, "min": 0.21615518629550934, "max": 13.435274124145508, "count": 40 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2615.70849609375, "min": 41.934104919433594, "max": 2752.503662109375, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 40 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07579438593757895, "min": 0.05704733592077829, "max": 0.07579438593757895, "count": 40 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3031775437503158, "min": 0.22818934368311317, "max": 0.3775441272252162, "count": 40 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17985403961410706, "min": 0.10064860916577792, "max": 0.2874147809457545, "count": 40 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7194161584564283, "min": 0.4025944366631117, "max": 1.3662724813409879, "count": 40 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.0001815564394812, "min": 0.0001815564394812, "max": 0.0002983764005411999, "count": 40 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0007262257579248, "min": 0.0007262257579248, "max": 0.001477032007656, "count": 40 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.16051880000000002, "min": 0.16051880000000002, "max": 0.1994588, "count": 40 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.6420752000000001, "min": 0.6420752000000001, "max": 0.992344, "count": 40 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00302988812, "min": 0.00302988812, "max": 0.00497299412, "count": 40 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.01211955248, "min": 0.01211955248, "max": 0.0246179656, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.204545454545453, "min": 2.75, "max": 26.62962962962963, "count": 40 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1153.0, "min": 121.0, "max": 1453.0, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.204545454545453, "min": 2.75, "max": 26.62962962962963, "count": 40 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1153.0, "min": 121.0, "max": 1453.0, "count": 40 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1678707056", "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": "1678707974" }, "total": 917.4854857490001, "count": 1, "self": 0.5555745460000026, "children": { "run_training.setup": { "total": 0.18040717899998526, "count": 1, "self": 0.18040717899998526 }, "TrainerController.start_learning": { "total": 916.7495040240001, "count": 1, "self": 1.0533329419977235, "children": { "TrainerController._reset_env": { "total": 8.932200663000003, "count": 1, "self": 8.932200663000003 }, "TrainerController.advance": { "total": 906.4849117500023, "count": 36875, "self": 0.5107798780045414, "children": { "env_step": { "total": 905.9741318719978, "count": 36875, "self": 659.255450651988, "children": { "SubprocessEnvManager._take_step": { "total": 246.21370160697967, "count": 36875, "self": 4.337070590982989, "children": { "TorchPolicy.evaluate": { "total": 241.87663101599668, "count": 36875, "self": 241.87663101599668 } } }, "workers": { "total": 0.5049796130301729, "count": 36874, "self": 0.0, "children": { "worker_root": { "total": 914.0125854119963, "count": 36874, "is_parallel": true, "self": 436.34508969799896, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005471386000010625, "count": 1, "is_parallel": true, "self": 0.0033464360000152737, "children": { "_process_rank_one_or_two_observation": { "total": 0.0021249499999953514, "count": 10, "is_parallel": true, "self": 0.0021249499999953514 } } }, "UnityEnvironment.step": { "total": 0.03359071199997743, "count": 1, "is_parallel": true, "self": 0.0005230380000398327, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00031345700000429133, "count": 1, "is_parallel": true, "self": 0.00031345700000429133 }, "communicator.exchange": { "total": 0.03091835599997239, "count": 1, "is_parallel": true, "self": 0.03091835599997239 }, "steps_from_proto": { "total": 0.0018358609999609143, "count": 1, "is_parallel": true, "self": 0.00038067599996338686, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014551849999975275, "count": 10, "is_parallel": true, "self": 0.0014551849999975275 } } } } } } }, "UnityEnvironment.step": { "total": 477.6674957139973, "count": 36873, "is_parallel": true, "self": 18.736864977998664, "children": { "UnityEnvironment._generate_step_input": { "total": 10.189210288018387, "count": 36873, "is_parallel": true, "self": 10.189210288018387 }, "communicator.exchange": { "total": 388.2129751029847, "count": 36873, "is_parallel": true, "self": 388.2129751029847 }, "steps_from_proto": { "total": 60.52844534499559, "count": 36873, "is_parallel": true, "self": 11.823293798027805, "children": { "_process_rank_one_or_two_observation": { "total": 48.705151546967784, "count": 368730, "is_parallel": true, "self": 48.705151546967784 } } } } } } } } } } } } }, "trainer_threads": { "total": 5.5661000033069286e-05, "count": 1, "self": 5.5661000033069286e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 900.2247008759799, "count": 749190, "is_parallel": true, "self": 18.063220108980772, "children": { "process_trajectory": { "total": 492.467188187999, "count": 749190, "is_parallel": true, "self": 490.40211844199894, "children": { "RLTrainer._checkpoint": { "total": 2.065069746000063, "count": 8, "is_parallel": true, "self": 2.065069746000063 } } }, "_update_policy": { "total": 389.6942925790001, "count": 184, "is_parallel": true, "self": 151.21674009101332, "children": { "TorchPPOOptimizer.update": { "total": 238.47755248798677, "count": 9381, "is_parallel": true, "self": 238.47755248798677 } } } } } } } } }, "TrainerController._save_models": { "total": 0.27900300800001787, "count": 1, "self": 0.0012815379998301069, "children": { "RLTrainer._checkpoint": { "total": 0.27772147000018776, "count": 1, "self": 0.27772147000018776 } } } } } } }