{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.6881552338600159, "min": 0.6706426739692688, "max": 2.858078718185425, "count": 200 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7085.24658203125, "min": 6511.775390625, "max": 29301.0234375, "count": 200 }, "SnowballTarget.Step.mean": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Step.sum": { "value": 1999992.0, "min": 9952.0, "max": 1999992.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 15.057650566101074, "min": 0.41388875246047974, "max": 15.063406944274902, "count": 200 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 3086.818359375, "min": 80.29441833496094, "max": 3086.818359375, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 200 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07093525221217516, "min": 0.061285341782886284, "max": 0.07554524878408606, "count": 200 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.3546762610608758, "min": 0.24514136713154513, "max": 0.37772624392043025, "count": 200 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.12574609148443913, "min": 0.10780366807810815, "max": 0.26156203499903863, "count": 200 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.6287304574221957, "min": 0.4312146723124326, "max": 1.2252386874135803, "count": 200 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 7.032997656000037e-07, "min": 7.032997656000037e-07, "max": 0.00029918820027059994, "count": 200 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.5164988280000187e-06, "min": 3.5164988280000187e-06, "max": 0.0014885160038279998, "count": 200 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10023440000000002, "min": 0.10023440000000002, "max": 0.19972939999999997, "count": 200 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5011720000000001, "min": 0.40291760000000004, "max": 0.9961720000000001, "count": 200 }, "SnowballTarget.Policy.Beta.mean": { "value": 2.1696560000000063e-05, "min": 2.1696560000000063e-05, "max": 0.004986497059999999, "count": 200 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.00010848280000000032, "min": 0.00010848280000000032, "max": 0.024808982799999997, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 29.163636363636364, "min": 3.8181818181818183, "max": 29.59090909090909, "count": 200 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1604.0, "min": 168.0, "max": 1620.0, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 29.163636363636364, "min": 3.8181818181818183, "max": 29.59090909090909, "count": 200 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1604.0, "min": 168.0, "max": 1620.0, "count": 200 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 200 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1701599794", "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "2.1.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1701605879" }, "total": 6085.639542335, "count": 1, "self": 0.4920440450005117, "children": { "run_training.setup": { "total": 0.06171481399996992, "count": 1, "self": 0.06171481399996992 }, "TrainerController.start_learning": { "total": 6085.085783476, "count": 1, "self": 6.0413206618250115, "children": { "TrainerController._reset_env": { "total": 3.419668664000028, "count": 1, "self": 3.419668664000028 }, "TrainerController.advance": { "total": 6075.507497021175, "count": 181870, "self": 3.1982791521695617, "children": { "env_step": { "total": 6072.309217869006, "count": 181870, "self": 4480.107600720082, "children": { "SubprocessEnvManager._take_step": { "total": 1589.0552716190264, "count": 181870, "self": 16.268267057058893, "children": { "TorchPolicy.evaluate": { "total": 1572.7870045619675, "count": 181870, "self": 1572.7870045619675 } } }, "workers": { "total": 3.146345529897417, "count": 181870, "self": 0.0, "children": { "worker_root": { "total": 6071.04655261503, "count": 181870, "is_parallel": true, "self": 3495.9336424649864, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00410251900007097, "count": 1, "is_parallel": true, "self": 0.0027207340003769787, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013817849996939913, "count": 10, "is_parallel": true, "self": 0.0013817849996939913 } } }, "UnityEnvironment.step": { "total": 0.05568750099996578, "count": 1, "is_parallel": true, "self": 0.0006568869998773152, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039282700004150684, "count": 1, "is_parallel": true, "self": 0.00039282700004150684 }, "communicator.exchange": { "total": 0.052825444000063726, "count": 1, "is_parallel": true, "self": 0.052825444000063726 }, "steps_from_proto": { "total": 0.0018123429999832297, "count": 1, "is_parallel": true, "self": 0.00034420700023929385, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014681359997439358, "count": 10, "is_parallel": true, "self": 0.0014681359997439358 } } } } } } }, "UnityEnvironment.step": { "total": 2575.1129101500437, "count": 181869, "is_parallel": true, "self": 114.49436324507678, "children": { "UnityEnvironment._generate_step_input": { "total": 58.08549776303903, "count": 181869, "is_parallel": true, "self": 58.08549776303903 }, "communicator.exchange": { "total": 2039.3539611080687, "count": 181869, "is_parallel": true, "self": 2039.3539611080687 }, "steps_from_proto": { "total": 363.17908803385956, "count": 181869, "is_parallel": true, "self": 69.23445757426566, "children": { "_process_rank_one_or_two_observation": { "total": 293.9446304595939, "count": 1818690, "is_parallel": true, "self": 293.9446304595939 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00033034900025086245, "count": 1, "self": 0.00033034900025086245, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 6033.238530590631, "count": 5046966, "is_parallel": true, "self": 117.39643506490393, "children": { "process_trajectory": { "total": 2750.3523224937308, "count": 5046966, "is_parallel": true, "self": 2742.383719872737, "children": { "RLTrainer._checkpoint": { "total": 7.968602620993806, "count": 40, "is_parallel": true, "self": 7.968602620993806 } } }, "_update_policy": { "total": 3165.4897730319963, "count": 909, "is_parallel": true, "self": 1142.568714140042, "children": { "TorchPPOOptimizer.update": { "total": 2022.9210588919543, "count": 92712, "is_parallel": true, "self": 2022.9210588919543 } } } } } } } } }, "TrainerController._save_models": { "total": 0.11696677999952954, "count": 1, "self": 0.002987400999700185, "children": { "RLTrainer._checkpoint": { "total": 0.11397937899982935, "count": 1, "self": 0.11397937899982935 } } } } } } }