{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 1.034855604171753, "min": 1.034855604171753, "max": 2.8629252910614014, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 9869.41796875, "min": 9869.41796875, "max": 29350.7109375, "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": 11.60657024383545, "min": 0.46763941645622253, "max": 11.60657024383545, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2263.28125, "min": 90.7220458984375, "max": 2345.394287109375, "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": 0.061529002928342805, "min": 0.05856181989014765, "max": 0.07731991138916426, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.24611601171337122, "min": 0.2342472795605906, "max": 0.3865995569458213, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.18411760886802395, "min": 0.14886739342496275, "max": 0.27672656172630833, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.7364704354720958, "min": 0.595469573699851, "max": 1.3836328086315417, "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": 23.022727272727273, "min": 3.8636363636363638, "max": 23.022727272727273, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1013.0, "min": 170.0, "max": 1248.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 23.022727272727273, "min": 3.8636363636363638, "max": 23.022727272727273, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1013.0, "min": 170.0, "max": 1248.0, "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": "1681060359", "python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]", "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": "1681060825" }, "total": 465.70569816899996, "count": 1, "self": 0.38440518599998086, "children": { "run_training.setup": { "total": 0.11075518500001635, "count": 1, "self": 0.11075518500001635 }, "TrainerController.start_learning": { "total": 465.21053779799996, "count": 1, "self": 0.561922749005987, "children": { "TrainerController._reset_env": { "total": 4.661471455999958, "count": 1, "self": 4.661471455999958 }, "TrainerController.advance": { "total": 459.84861018999413, "count": 18201, "self": 0.2902355199925637, "children": { "env_step": { "total": 459.55837467000157, "count": 18201, "self": 335.5300557890033, "children": { "SubprocessEnvManager._take_step": { "total": 123.74528813499938, "count": 18201, "self": 1.8588768160006452, "children": { "TorchPolicy.evaluate": { "total": 121.88641131899874, "count": 18201, "self": 121.88641131899874 } } }, "workers": { "total": 0.2830307459988717, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 463.7243350590088, "count": 18201, "is_parallel": true, "self": 215.62689087900014, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005211126999995486, "count": 1, "is_parallel": true, "self": 0.0035921259999440736, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016190010000514121, "count": 10, "is_parallel": true, "self": 0.0016190010000514121 } } }, "UnityEnvironment.step": { "total": 0.14168904399997473, "count": 1, "is_parallel": true, "self": 0.0006762250000065251, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00039631200002077094, "count": 1, "is_parallel": true, "self": 0.00039631200002077094 }, "communicator.exchange": { "total": 0.13627784799996334, "count": 1, "is_parallel": true, "self": 0.13627784799996334 }, "steps_from_proto": { "total": 0.004338658999984091, "count": 1, "is_parallel": true, "self": 0.00047658499988756375, "children": { "_process_rank_one_or_two_observation": { "total": 0.003862074000096527, "count": 10, "is_parallel": true, "self": 0.003862074000096527 } } } } } } }, "UnityEnvironment.step": { "total": 248.09744418000867, "count": 18200, "is_parallel": true, "self": 9.929399534995014, "children": { "UnityEnvironment._generate_step_input": { "total": 5.683539081001641, "count": 18200, "is_parallel": true, "self": 5.683539081001641 }, "communicator.exchange": { "total": 199.74499639001135, "count": 18200, "is_parallel": true, "self": 199.74499639001135 }, "steps_from_proto": { "total": 32.73950917400066, "count": 18200, "is_parallel": true, "self": 6.647716983973567, "children": { "_process_rank_one_or_two_observation": { "total": 26.091792190027093, "count": 182000, "is_parallel": true, "self": 26.091792190027093 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0003926259998934256, "count": 1, "self": 0.0003926259998934256, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 456.18218141300775, "count": 426840, "is_parallel": true, "self": 10.232797677007113, "children": { "process_trajectory": { "total": 251.22422605800045, "count": 426840, "is_parallel": true, "self": 250.4281699540005, "children": { "RLTrainer._checkpoint": { "total": 0.7960561039999448, "count": 4, "is_parallel": true, "self": 0.7960561039999448 } } }, "_update_policy": { "total": 194.7251576780002, "count": 90, "is_parallel": true, "self": 75.9412217180008, "children": { "TorchPPOOptimizer.update": { "total": 118.78393595999938, "count": 4587, "is_parallel": true, "self": 118.78393595999938 } } } } } } } } }, "TrainerController._save_models": { "total": 0.1381407769999896, "count": 1, "self": 0.0009212199998955839, "children": { "RLTrainer._checkpoint": { "total": 0.13721955700009403, "count": 1, "self": 0.13721955700009403 } } } } } } }