{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9495184421539307, "min": 0.9261974096298218, "max": 2.8737332820892334, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9066.001953125, "min": 9066.001953125, "max": 29493.125, "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": 12.709700584411621, "min": 0.2641322910785675, "max": 12.709700584411621, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2478.3916015625, "min": 51.24166488647461, "max": 2584.094970703125, "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": 0.06797929171657682, "min": 0.062448795563450045, "max": 0.07740195319638588, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2719171668663073, "min": 0.25259485129850767, "max": 0.37254929514807267, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19822486292789965, "min": 0.10124634682114107, "max": 0.27497581021458495, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7928994517115986, "min": 0.4049853872845643, "max": 1.3748790510729247, "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": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1120.0, "min": 141.0, "max": 1356.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.454545454545453, "min": 3.2045454545454546, "max": 25.454545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1120.0, "min": 141.0, "max": 1356.0, "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": "1691079555", "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": "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": "1691080027" }, "total": 472.12433767799985, "count": 1, "self": 0.4410912929999995, "children": { "run_training.setup": { "total": 0.04340297399994597, "count": 1, "self": 0.04340297399994597 }, "TrainerController.start_learning": { "total": 471.6398434109999, "count": 1, "self": 0.5526199510154584, "children": { "TrainerController._reset_env": { "total": 5.422263750999946, "count": 1, "self": 5.422263750999946 }, "TrainerController.advance": { "total": 465.52649140398444, "count": 18201, "self": 0.2557034929893689, "children": { "env_step": { "total": 465.27078791099507, "count": 18201, "self": 339.46623061699506, "children": { "SubprocessEnvManager._take_step": { "total": 125.5239599629856, "count": 18201, "self": 1.9250726989810119, "children": { "TorchPolicy.evaluate": { "total": 123.59888726400459, "count": 18201, "self": 123.59888726400459 } } }, "workers": { "total": 0.2805973310144054, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 470.0721438109799, "count": 18201, "is_parallel": true, "self": 221.98874148700315, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0053492009999445145, "count": 1, "is_parallel": true, "self": 0.003861163000237866, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014880379997066484, "count": 10, "is_parallel": true, "self": 0.0014880379997066484 } } }, "UnityEnvironment.step": { "total": 0.0938918559998001, "count": 1, "is_parallel": true, "self": 0.0006391609997535852, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00045959199997014366, "count": 1, "is_parallel": true, "self": 0.00045959199997014366 }, "communicator.exchange": { "total": 0.0905850350000037, "count": 1, "is_parallel": true, "self": 0.0905850350000037 }, "steps_from_proto": { "total": 0.0022080680000726716, "count": 1, "is_parallel": true, "self": 0.0004045329999371461, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018035350001355255, "count": 10, "is_parallel": true, "self": 0.0018035350001355255 } } } } } } }, "UnityEnvironment.step": { "total": 248.08340232397677, "count": 18200, "is_parallel": true, "self": 10.650374613968324, "children": { "UnityEnvironment._generate_step_input": { "total": 5.253971908992298, "count": 18200, "is_parallel": true, "self": 5.253971908992298 }, "communicator.exchange": { "total": 196.11837761099991, "count": 18200, "is_parallel": true, "self": 196.11837761099991 }, "steps_from_proto": { "total": 36.06067819001623, "count": 18200, "is_parallel": true, "self": 6.583068142958155, "children": { "_process_rank_one_or_two_observation": { "total": 29.47761004705808, "count": 182000, "is_parallel": true, "self": 29.47761004705808 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014880999992783472, "count": 1, "self": 0.00014880999992783472, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 462.1236437290513, "count": 432345, "is_parallel": true, "self": 9.34745201813439, "children": { "process_trajectory": { "total": 251.59376183391714, "count": 432345, "is_parallel": true, "self": 250.8194571909171, "children": { "RLTrainer._checkpoint": { "total": 0.7743046430000504, "count": 4, "is_parallel": true, "self": 0.7743046430000504 } } }, "_update_policy": { "total": 201.18242987699978, "count": 90, "is_parallel": true, "self": 79.31962191198977, "children": { "TorchPPOOptimizer.update": { "total": 121.86280796501, "count": 4587, "is_parallel": true, "self": 121.86280796501 } } } } } } } } }, "TrainerController._save_models": { "total": 0.13831949500013252, "count": 1, "self": 0.0011122820001219225, "children": { "RLTrainer._checkpoint": { "total": 0.1372072130000106, "count": 1, "self": 0.1372072130000106 } } } } } } }