{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7779006958007812, "min": 0.7779006958007812, "max": 2.849827527999878, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7393.16796875, "min": 7393.16796875, "max": 29091.0390625, "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": 12.843145370483398, "min": 0.4330281615257263, "max": 12.843145370483398, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2504.413330078125, "min": 84.00746154785156, "max": 2586.950927734375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06706359152895838, "min": 0.061115813709358355, "max": 0.07893689773962642, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.26825436611583353, "min": 0.24446325483743342, "max": 0.3654424306918301, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17203085427629014, "min": 0.13083257453114377, "max": 0.2665379536502502, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6881234171051606, "min": 0.5233302981245751, "max": 1.3326897682512509, "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.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.Environment.CumulativeReward.mean": { "value": 26.068181818181817, "min": 3.909090909090909, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1147.0, "min": 172.0, "max": 1394.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.068181818181817, "min": 3.909090909090909, "max": 26.068181818181817, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1147.0, "min": 172.0, "max": 1394.0, "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": "1784790138", "python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]", "command_line_arguments": "/content/mlagents310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1784790613" }, "total": 474.1863099860002, "count": 1, "self": 0.5463099740004509, "children": { "run_training.setup": { "total": 0.03332833199965535, "count": 1, "self": 0.03332833199965535 }, "TrainerController.start_learning": { "total": 473.6066716800001, "count": 1, "self": 0.42658592700445297, "children": { "TrainerController._reset_env": { "total": 3.2968773540001166, "count": 1, "self": 3.2968773540001166 }, "TrainerController.advance": { "total": 469.79842952399576, "count": 18192, "self": 0.4412710759938818, "children": { "env_step": { "total": 347.6938111309937, "count": 18192, "self": 272.71696142401424, "children": { "SubprocessEnvManager._take_step": { "total": 74.71892968798238, "count": 18192, "self": 1.3701296909653138, "children": { "TorchPolicy.evaluate": { "total": 73.34879999701707, "count": 18192, "self": 73.34879999701707 } } }, "workers": { "total": 0.2579200189970834, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 471.6785286200102, "count": 18192, "is_parallel": true, "self": 232.88841133403412, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004204738999760593, "count": 1, "is_parallel": true, "self": 0.0028479069992499717, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013568320005106216, "count": 10, "is_parallel": true, "self": 0.0013568320005106216 } } }, "UnityEnvironment.step": { "total": 0.03647393900018869, "count": 1, "is_parallel": true, "self": 0.0005945039997641288, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003712399998221372, "count": 1, "is_parallel": true, "self": 0.0003712399998221372 }, "communicator.exchange": { "total": 0.03341930800024784, "count": 1, "is_parallel": true, "self": 0.03341930800024784 }, "steps_from_proto": { "total": 0.002088887000354589, "count": 1, "is_parallel": true, "self": 0.00039055100114637753, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016983359992082114, "count": 10, "is_parallel": true, "self": 0.0016983359992082114 } } } } } } }, "UnityEnvironment.step": { "total": 238.79011728597607, "count": 18191, "is_parallel": true, "self": 10.785249392962669, "children": { "UnityEnvironment._generate_step_input": { "total": 5.79951832002871, "count": 18191, "is_parallel": true, "self": 5.79951832002871 }, "communicator.exchange": { "total": 183.28368747898094, "count": 18191, "is_parallel": true, "self": 183.28368747898094 }, "steps_from_proto": { "total": 38.92166209400375, "count": 18191, "is_parallel": true, "self": 6.90701346899732, "children": { "_process_rank_one_or_two_observation": { "total": 32.01464862500643, "count": 181910, "is_parallel": true, "self": 32.01464862500643 } } } } } } } } } } }, "trainer_advance": { "total": 121.66334731700817, "count": 18192, "self": 0.5262211470103466, "children": { "process_trajectory": { "total": 24.96930865299646, "count": 18192, "self": 24.552485796995825, "children": { "RLTrainer._checkpoint": { "total": 0.4168228560006355, "count": 4, "self": 0.4168228560006355 } } }, "_update_policy": { "total": 96.16781751700137, "count": 90, "self": 39.38624205000224, "children": { "TorchPPOOptimizer.update": { "total": 56.78157546699913, "count": 4587, "self": 56.78157546699913 } } } } } } }, "trainer_threads": { "total": 1.0799999472510535e-06, "count": 1, "self": 1.0799999472510535e-06 }, "TrainerController._save_models": { "total": 0.08477779499980898, "count": 1, "self": 0.0007671889998164261, "children": { "RLTrainer._checkpoint": { "total": 0.08401060599999255, "count": 1, "self": 0.08401060599999255 } } } } } } }