{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8896070718765259, "min": 0.8896070718765259, "max": 2.855018377304077, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8484.1826171875, "min": 8484.1826171875, "max": 29332.458984375, "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": 12.958393096923828, "min": 0.5116788148880005, "max": 12.958393096923828, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2526.88671875, "min": 99.26569366455078, "max": 2606.1181640625, "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": 0.07566580776177693, "min": 0.060744819328772126, "max": 0.0758801312304522, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.30266323104710774, "min": 0.2429792773150885, "max": 0.379400656152261, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18260941384177581, "min": 0.10960015480968115, "max": 0.2724079555448364, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7304376553671033, "min": 0.4384006192387246, "max": 1.3263803884094836, "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": 25.886363636363637, "min": 3.2045454545454546, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1139.0, "min": 141.0, "max": 1391.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.886363636363637, "min": 3.2045454545454546, "max": 25.886363636363637, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1139.0, "min": 141.0, "max": 1391.0, "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": "1685038566", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "1685039070" }, "total": 503.61446592799996, "count": 1, "self": 0.43748243699997147, "children": { "run_training.setup": { "total": 0.05825827199998912, "count": 1, "self": 0.05825827199998912 }, "TrainerController.start_learning": { "total": 503.118725219, "count": 1, "self": 0.6648486630036246, "children": { "TrainerController._reset_env": { "total": 5.226639699000032, "count": 1, "self": 5.226639699000032 }, "TrainerController.advance": { "total": 497.0850647039963, "count": 18200, "self": 0.3167327649874778, "children": { "env_step": { "total": 496.7683319390088, "count": 18200, "self": 364.57363418500483, "children": { "SubprocessEnvManager._take_step": { "total": 131.87744954899603, "count": 18200, "self": 2.03783001499545, "children": { "TorchPolicy.evaluate": { "total": 129.83961953400058, "count": 18200, "self": 129.83961953400058 } } }, "workers": { "total": 0.3172482050079566, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 501.3296484580003, "count": 18200, "is_parallel": true, "self": 232.84108083999985, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0063367129999960525, "count": 1, "is_parallel": true, "self": 0.004027578000034282, "children": { "_process_rank_one_or_two_observation": { "total": 0.0023091349999617705, "count": 10, "is_parallel": true, "self": 0.0023091349999617705 } } }, "UnityEnvironment.step": { "total": 0.05529772100004493, "count": 1, "is_parallel": true, "self": 0.0006569500000637163, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004359799999633651, "count": 1, "is_parallel": true, "self": 0.0004359799999633651 }, "communicator.exchange": { "total": 0.051980592999996134, "count": 1, "is_parallel": true, "self": 0.051980592999996134 }, "steps_from_proto": { "total": 0.0022241980000217154, "count": 1, "is_parallel": true, "self": 0.00040468000008786476, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018195179999338507, "count": 10, "is_parallel": true, "self": 0.0018195179999338507 } } } } } } }, "UnityEnvironment.step": { "total": 268.48856761800045, "count": 18199, "is_parallel": true, "self": 10.547216987005584, "children": { "UnityEnvironment._generate_step_input": { "total": 5.729841075998195, "count": 18199, "is_parallel": true, "self": 5.729841075998195 }, "communicator.exchange": { "total": 216.45890865499587, "count": 18199, "is_parallel": true, "self": 216.45890865499587 }, "steps_from_proto": { "total": 35.7526009000008, "count": 18199, "is_parallel": true, "self": 7.076034162012775, "children": { "_process_rank_one_or_two_observation": { "total": 28.676566737988026, "count": 181990, "is_parallel": true, "self": 28.676566737988026 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00018168000008245144, "count": 1, "self": 0.00018168000008245144, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 493.4329823420012, "count": 474167, "is_parallel": true, "self": 10.524623854968866, "children": { "process_trajectory": { "total": 272.01288453003224, "count": 474167, "is_parallel": true, "self": 271.2045038980322, "children": { "RLTrainer._checkpoint": { "total": 0.8083806320000235, "count": 4, "is_parallel": true, "self": 0.8083806320000235 } } }, "_update_policy": { "total": 210.8954739570001, "count": 90, "is_parallel": true, "self": 78.84421818299904, "children": { "TorchPPOOptimizer.update": { "total": 132.05125577400105, "count": 4587, "is_parallel": true, "self": 132.05125577400105 } } } } } } } } }, "TrainerController._save_models": { "total": 0.14199047299996437, "count": 1, "self": 0.0009731720000445421, "children": { "RLTrainer._checkpoint": { "total": 0.14101730099991983, "count": 1, "self": 0.14101730099991983 } } } } } } }