{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.4443506002426147, "min": 1.4443506002426147, "max": 2.8682520389556885, "count": 10 }, "SnowballTarget.Policy.Entropy.sum": { "value": 14855.146484375, "min": 14855.146484375, "max": 29405.3203125, "count": 10 }, "SnowballTarget.Step.mean": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Step.sum": { "value": 99960.0, "min": 9952.0, "max": 99960.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 10.224575996398926, "min": 0.34794822335243225, "max": 10.224575996398926, "count": 10 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2085.8134765625, "min": 67.501953125, "max": 2085.8134765625, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 10 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06706761522926206, "min": 0.06374601766112713, "max": 0.07740271848366213, "count": 10 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.33533807614631034, "min": 0.2549840706445085, "max": 0.3870135924183107, "count": 10 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.24406272681320415, "min": 0.11358000970829059, "max": 0.29760017774853054, "count": 10 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 1.2203136340660208, "min": 0.45432003883316235, "max": 1.4880008887426526, "count": 10 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 0.00015823204725600002, "min": 0.00015823204725600002, "max": 0.000291882002706, "count": 10 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 0.0007911602362800001, "min": 0.0006923281692239998, "max": 0.00138516003828, "count": 10 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.15274400000000002, "min": 0.15274400000000002, "max": 0.19729400000000002, "count": 10 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.7637200000000001, "min": 0.630776, "max": 0.96172, "count": 10 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0026419256000000005, "min": 0.0026419256000000005, "max": 0.0048649706, "count": 10 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.013209628000000003, "min": 0.0115557224, "max": 0.023089828, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 22.418181818181818, "min": 3.2045454545454546, "max": 22.418181818181818, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1233.0, "min": 141.0, "max": 1233.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 22.418181818181818, "min": 3.2045454545454546, "max": 22.418181818181818, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1233.0, "min": 141.0, "max": 1233.0, "count": 10 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1700711722", "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1700711988" }, "total": 266.07658268599994, "count": 1, "self": 0.022479369999928167, "children": { "run_training.setup": { "total": 0.050861248000046544, "count": 1, "self": 0.050861248000046544 }, "TrainerController.start_learning": { "total": 266.00324206799996, "count": 1, "self": 1.309739751000734, "children": { "TrainerController._reset_env": { "total": 10.071572529000036, "count": 1, "self": 10.071572529000036 }, "TrainerController.advance": { "total": 254.33402336399922, "count": 9838, "self": 0.14260155799797758, "children": { "env_step": { "total": 254.19142180600124, "count": 9838, "self": 174.07370957299963, "children": { "SubprocessEnvManager._take_step": { "total": 79.96991609099109, "count": 9838, "self": 0.7986326559930603, "children": { "TorchPolicy.evaluate": { "total": 79.17128343499803, "count": 9838, "self": 79.17128343499803 } } }, "workers": { "total": 0.14779614201052027, "count": 9837, "self": 0.0, "children": { "worker_root": { "total": 263.99683453199873, "count": 9837, "is_parallel": true, "self": 133.0242820989963, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005483247000029223, "count": 1, "is_parallel": true, "self": 0.00405625999997028, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014269870000589435, "count": 10, "is_parallel": true, "self": 0.0014269870000589435 } } }, "UnityEnvironment.step": { "total": 0.037279034999983196, "count": 1, "is_parallel": true, "self": 0.0006527600000936218, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003771709999682571, "count": 1, "is_parallel": true, "self": 0.0003771709999682571 }, "communicator.exchange": { "total": 0.03429370999992898, "count": 1, "is_parallel": true, "self": 0.03429370999992898 }, "steps_from_proto": { "total": 0.0019553939999923386, "count": 1, "is_parallel": true, "self": 0.0003470769999012191, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016083170000911196, "count": 10, "is_parallel": true, "self": 0.0016083170000911196 } } } } } } }, "UnityEnvironment.step": { "total": 130.97255243300242, "count": 9836, "is_parallel": true, "self": 5.782640055000343, "children": { "UnityEnvironment._generate_step_input": { "total": 2.8969302549911617, "count": 9836, "is_parallel": true, "self": 2.8969302549911617 }, "communicator.exchange": { "total": 104.01514634500006, "count": 9836, "is_parallel": true, "self": 104.01514634500006 }, "steps_from_proto": { "total": 18.277835778010854, "count": 9836, "is_parallel": true, "self": 3.4484095200056117, "children": { "_process_rank_one_or_two_observation": { "total": 14.829426258005242, "count": 98360, "is_parallel": true, "self": 14.829426258005242 } } } } } } } } } } } } }, "trainer_threads": { "total": 6.430799999179726e-05, "count": 1, "self": 6.430799999179726e-05, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 251.05741148600248, "count": 265556, "is_parallel": true, "self": 5.2788834919998635, "children": { "process_trajectory": { "total": 142.1128230670023, "count": 265557, "is_parallel": true, "self": 141.52532722300225, "children": { "RLTrainer._checkpoint": { "total": 0.5874958440000455, "count": 2, "is_parallel": true, "self": 0.5874958440000455 } } }, "_update_policy": { "total": 103.66570492700032, "count": 48, "is_parallel": true, "self": 34.53346243999317, "children": { "TorchPPOOptimizer.update": { "total": 69.13224248700715, "count": 2479, "is_parallel": true, "self": 69.13224248700715 } } } } } } } } }, "TrainerController._save_models": { "total": 0.2878421159999789, "count": 1, "self": 0.0009594870000455558, "children": { "RLTrainer._checkpoint": { "total": 0.28688262899993333, "count": 1, "self": 0.28688262899993333 } } } } } } }