{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.9948765635490417, "min": 0.9948765635490417, "max": 2.854140520095825, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9488.1376953125, "min": 9488.1376953125, "max": 29260.6484375, "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": 11.752761840820312, "min": 0.3440046012401581, "max": 11.840299606323242, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2291.78857421875, "min": 66.73689270019531, "max": 2414.733154296875, "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": 0.06498726546095557, "min": 0.06341112932307393, "max": 0.07124503661590793, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25994906184382227, "min": 0.2536445172922957, "max": 0.35622518307953965, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.19988109828794706, "min": 0.12420741644774692, "max": 0.2859034519277367, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7995243931517882, "min": 0.4968296657909877, "max": 1.3119546049365811, "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": 23.5, "min": 3.522727272727273, "max": 23.59090909090909, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1034.0, "min": 155.0, "max": 1268.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.5, "min": 3.522727272727273, "max": 23.59090909090909, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1034.0, "min": 155.0, "max": 1268.0, "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": "1722589599", "python_version": "3.10.12 (main, Jul 29 2024, 16:56:48) [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": "2.3.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1722590071" }, "total": 471.6918207780001, "count": 1, "self": 0.4425347220000049, "children": { "run_training.setup": { "total": 0.06161932700001671, "count": 1, "self": 0.06161932700001671 }, "TrainerController.start_learning": { "total": 471.18766672900006, "count": 1, "self": 0.6408627159948992, "children": { "TrainerController._reset_env": { "total": 2.79553205600007, "count": 1, "self": 2.79553205600007 }, "TrainerController.advance": { "total": 467.65636033500493, "count": 18200, "self": 0.29511856997498853, "children": { "env_step": { "total": 467.36124176502994, "count": 18200, "self": 303.4393854710271, "children": { "SubprocessEnvManager._take_step": { "total": 163.61363382501224, "count": 18200, "self": 1.5830020460145988, "children": { "TorchPolicy.evaluate": { "total": 162.03063177899764, "count": 18200, "self": 162.03063177899764 } } }, "workers": { "total": 0.308222468990607, "count": 18200, "self": 0.0, "children": { "worker_root": { "total": 469.92420736398935, "count": 18200, "is_parallel": true, "self": 237.19848165699955, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00758962200006863, "count": 1, "is_parallel": true, "self": 0.006004045000054248, "children": { "_process_rank_one_or_two_observation": { "total": 0.001585577000014382, "count": 10, "is_parallel": true, "self": 0.001585577000014382 } } }, "UnityEnvironment.step": { "total": 0.12737056100002064, "count": 1, "is_parallel": true, "self": 0.0007509920001211867, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00046217700003126083, "count": 1, "is_parallel": true, "self": 0.00046217700003126083 }, "communicator.exchange": { "total": 0.12378085499994995, "count": 1, "is_parallel": true, "self": 0.12378085499994995 }, "steps_from_proto": { "total": 0.002376536999918244, "count": 1, "is_parallel": true, "self": 0.0004666400000132853, "children": { "_process_rank_one_or_two_observation": { "total": 0.0019098969999049586, "count": 10, "is_parallel": true, "self": 0.0019098969999049586 } } } } } } }, "UnityEnvironment.step": { "total": 232.7257257069898, "count": 18199, "is_parallel": true, "self": 10.51877739397844, "children": { "UnityEnvironment._generate_step_input": { "total": 5.563356612000689, "count": 18199, "is_parallel": true, "self": 5.563356612000689 }, "communicator.exchange": { "total": 181.81136577401026, "count": 18199, "is_parallel": true, "self": 181.81136577401026 }, "steps_from_proto": { "total": 34.83222592700042, "count": 18199, "is_parallel": true, "self": 6.750466550963779, "children": { "_process_rank_one_or_two_observation": { "total": 28.081759376036644, "count": 181990, "is_parallel": true, "self": 28.081759376036644 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00015646500014554476, "count": 1, "self": 0.00015646500014554476, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 461.8842060150009, "count": 709827, "is_parallel": true, "self": 15.008013342029585, "children": { "process_trajectory": { "total": 256.1724573459712, "count": 709827, "is_parallel": true, "self": 255.2887828809712, "children": { "RLTrainer._checkpoint": { "total": 0.8836744650000128, "count": 4, "is_parallel": true, "self": 0.8836744650000128 } } }, "_update_policy": { "total": 190.70373532700012, "count": 90, "is_parallel": true, "self": 59.99488242199311, "children": { "TorchPPOOptimizer.update": { "total": 130.708852905007, "count": 4584, "is_parallel": true, "self": 130.708852905007 } } } } } } } } }, "TrainerController._save_models": { "total": 0.0947551570000087, "count": 1, "self": 0.0011061510001582064, "children": { "RLTrainer._checkpoint": { "total": 0.09364900599985049, "count": 1, "self": 0.09364900599985049 } } } } } } }