{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 2.6788556575775146, "min": 2.6775705814361572, "max": 2.890324354171753, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 3978.1005859375, "min": 1855.556396484375, "max": 4185.9599609375, "count": 20 }, "SnowballTarget.Step.mean": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 19992.0, "min": 960.0, "max": 19992.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 2.1473498344421387, "min": -0.07521140575408936, "max": 2.1473498344421387, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 55.83109664916992, "min": -1.2033824920654297, "max": 55.83109664916992, "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 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 9 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 2189.0, "min": 2189.0, "max": 2189.0, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06899261169646885, "min": 0.06055742186293298, "max": 0.07794120928213256, "count": 9 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.06899261169646885, "min": 0.06055742186293298, "max": 0.07794120928213256, "count": 9 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2524205738422917, "min": 0.09193896502256393, "max": 0.2813739899326773, "count": 9 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.2524205738422917, "min": 0.09193896502256393, "max": 0.2813739899326773, "count": 9 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 1.4400098559999969e-05, "min": 1.4400098559999969e-05, "max": 0.00089440001056, "count": 9 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 1.4400098559999969e-05, "min": 1.4400098559999969e-05, "max": 0.00089440001056, "count": 9 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.10144, "min": 0.10144, "max": 0.18944000000000003, "count": 9 }, "SnowballTarget.Policy.Beta.mean": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Policy.Beta.sum": { "value": 8.185599999999986e-05, "min": 8.185599999999986e-05, "max": 0.0044730559999999996, "count": 9 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 8.181818181818182, "min": 2.272727272727273, "max": 8.181818181818182, "count": 10 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 90.0, "min": 5.0, "max": 90.0, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 8.181818181818182, "min": 2.272727272727273, "max": 8.181818181818182, "count": 10 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 90.0, "min": 5.0, "max": 90.0, "count": 10 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1715891532", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]", "command_line_arguments": "/usr/local/bin/mlagents-learn /content/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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715891583" }, "total": 50.979097178000075, "count": 1, "self": 0.4478481560000773, "children": { "run_training.setup": { "total": 0.05625610599997799, "count": 1, "self": 0.05625610599997799 }, "TrainerController.start_learning": { "total": 50.47499291600002, "count": 1, "self": 0.08132929699888791, "children": { "TrainerController._reset_env": { "total": 3.4105121349999763, "count": 1, "self": 3.4105121349999763 }, "TrainerController.advance": { "total": 46.89521004800122, "count": 1871, "self": 0.025772283999344836, "children": { "env_step": { "total": 46.86943776400187, "count": 1871, "self": 29.633547662001774, "children": { "SubprocessEnvManager._take_step": { "total": 17.20989406299998, "count": 1871, "self": 0.15427301700117368, "children": { "TorchPolicy.evaluate": { "total": 17.055621045998805, "count": 1871, "self": 17.055621045998805 } } }, "workers": { "total": 0.02599603900011971, "count": 1871, "self": 0.0, "children": { "worker_root": { "total": 50.25248729600116, "count": 1871, "is_parallel": true, "self": 27.664702424007373, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005320769000036307, "count": 1, "is_parallel": true, "self": 0.003860969000015757, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014598000000205502, "count": 10, "is_parallel": true, "self": 0.0014598000000205502 } } }, "UnityEnvironment.step": { "total": 0.03632874499999161, "count": 1, "is_parallel": true, "self": 0.0006854340000472803, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039413399997556553, "count": 1, "is_parallel": true, "self": 0.00039413399997556553 }, "communicator.exchange": { "total": 0.033119478000003255, "count": 1, "is_parallel": true, "self": 0.033119478000003255 }, "steps_from_proto": { "total": 0.0021296989999655125, "count": 1, "is_parallel": true, "self": 0.0006112800001574215, "children": { "_process_rank_one_or_two_observation": { "total": 0.001518418999808091, "count": 10, "is_parallel": true, "self": 0.001518418999808091 } } } } } } }, "UnityEnvironment.step": { "total": 22.58778487199379, "count": 1870, "is_parallel": true, "self": 1.019031279996625, "children": { "UnityEnvironment._generate_step_input": { "total": 0.5401405770016936, "count": 1870, "is_parallel": true, "self": 0.5401405770016936 }, "communicator.exchange": { "total": 17.625984907997008, "count": 1870, "is_parallel": true, "self": 17.625984907997008 }, "steps_from_proto": { "total": 3.4026281069984634, "count": 1870, "is_parallel": true, "self": 0.6428753099964979, "children": { "_process_rank_one_or_two_observation": { "total": 2.7597527970019655, "count": 18700, "is_parallel": true, "self": 2.7597527970019655 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0002529659999481737, "count": 1, "self": 0.0002529659999481737, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 46.36920315899556, "count": 68722, "is_parallel": true, "self": 1.3887293310086761, "children": { "process_trajectory": { "total": 25.92100388598692, "count": 68722, "is_parallel": true, "self": 25.052068088986744, "children": { "RLTrainer._checkpoint": { "total": 0.8689357970001765, "count": 4, "is_parallel": true, "self": 0.8689357970001765 } } }, "_update_policy": { "total": 19.059469941999964, "count": 9, "is_parallel": true, "self": 5.820686683999497, "children": { "TorchPPOOptimizer.update": { "total": 13.238783258000467, "count": 456, "is_parallel": true, "self": 13.238783258000467 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08768846999998914, "count": 1, "self": 0.0009447510000200054, "children": { "RLTrainer._checkpoint": { "total": 0.08674371899996913, "count": 1, "self": 0.08674371899996913 } } } } } } }