{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8224050998687744, "min": 0.795151948928833, "max": 2.8327841758728027, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 7870.4169921875, "min": 7714.564453125, "max": 29010.54296875, "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": 12.900566101074219, "min": 0.30364859104156494, "max": 12.900566101074219, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.6103515625, "min": 58.9078254699707, "max": 2610.82763671875, "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": 0.07312035393061153, "min": 0.062356037706337575, "max": 0.07503787594919856, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.2924814157224461, "min": 0.25606686731614403, "max": 0.37518937974599276, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.1263689571516771, "min": 0.0854786709407527, "max": 0.18331826422728742, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.5054758286067084, "min": 0.3419146837630108, "max": 0.9165913211364372, "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": 0.10538800000000001, "min": 0.10538800000000001, "max": 0.29458799999999996, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.42155200000000004, "min": 0.42155200000000004, "max": 1.42344, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.00027913060000000025, "min": 0.00027913060000000025, "max": 0.009729670599999999, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.001116522400000001, "min": 0.001116522400000001, "max": 0.046175827999999995, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.59090909090909, "min": 4.159090909090909, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1126.0, "min": 183.0, "max": 1415.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.59090909090909, "min": 4.159090909090909, "max": 25.727272727272727, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1126.0, "min": 183.0, "max": 1415.0, "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": "1698497456", "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": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.1.0+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1698497920" }, "total": 464.11340836, "count": 1, "self": 0.4243672739999056, "children": { "run_training.setup": { "total": 0.04387820500005546, "count": 1, "self": 0.04387820500005546 }, "TrainerController.start_learning": { "total": 463.64516288100003, "count": 1, "self": 0.5596854150044237, "children": { "TrainerController._reset_env": { "total": 8.773025900999983, "count": 1, "self": 8.773025900999983 }, "TrainerController.advance": { "total": 454.22866953499533, "count": 18201, "self": 0.25780259800512795, "children": { "env_step": { "total": 453.9708669369902, "count": 18201, "self": 308.9326041849404, "children": { "SubprocessEnvManager._take_step": { "total": 144.7696967229981, "count": 18201, "self": 1.4216266289872692, "children": { "TorchPolicy.evaluate": { "total": 143.34807009401084, "count": 18201, "self": 143.34807009401084 } } }, "workers": { "total": 0.2685660290517262, "count": 18201, "self": 0.0, "children": { "worker_root": { "total": 462.257796792981, "count": 18201, "is_parallel": true, "self": 226.6901713529801, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.005529073999696266, "count": 1, "is_parallel": true, "self": 0.004108241998892481, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014208320008037845, "count": 10, "is_parallel": true, "self": 0.0014208320008037845 } } }, "UnityEnvironment.step": { "total": 0.04840695199982292, "count": 1, "is_parallel": true, "self": 0.0006257600002754771, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003754790000130015, "count": 1, "is_parallel": true, "self": 0.0003754790000130015 }, "communicator.exchange": { "total": 0.045588371999656374, "count": 1, "is_parallel": true, "self": 0.045588371999656374 }, "steps_from_proto": { "total": 0.0018173409998780699, "count": 1, "is_parallel": true, "self": 0.00035934300012741005, "children": { "_process_rank_one_or_two_observation": { "total": 0.0014579979997506598, "count": 10, "is_parallel": true, "self": 0.0014579979997506598 } } } } } } }, "UnityEnvironment.step": { "total": 235.56762544000094, "count": 18200, "is_parallel": true, "self": 10.53761140100778, "children": { "UnityEnvironment._generate_step_input": { "total": 5.449538566970659, "count": 18200, "is_parallel": true, "self": 5.449538566970659 }, "communicator.exchange": { "total": 186.05103101099985, "count": 18200, "is_parallel": true, "self": 186.05103101099985 }, "steps_from_proto": { "total": 33.52944446102265, "count": 18200, "is_parallel": true, "self": 6.210296462110364, "children": { "_process_rank_one_or_two_observation": { "total": 27.319147998912285, "count": 182000, "is_parallel": true, "self": 27.319147998912285 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.00014412100017580087, "count": 1, "self": 0.00014412100017580087, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 450.4210468791207, "count": 467672, "is_parallel": true, "self": 9.905689852176693, "children": { "process_trajectory": { "total": 253.60032187994466, "count": 467672, "is_parallel": true, "self": 252.81520573694525, "children": { "RLTrainer._checkpoint": { "total": 0.7851161429994136, "count": 4, "is_parallel": true, "self": 0.7851161429994136 } } }, "_update_policy": { "total": 186.91503514699934, "count": 90, "is_parallel": true, "self": 57.62690087899091, "children": { "TorchPPOOptimizer.update": { "total": 129.28813426800843, "count": 4584, "is_parallel": true, "self": 129.28813426800843 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08363790900011736, "count": 1, "self": 0.0008400020001317898, "children": { "RLTrainer._checkpoint": { "total": 0.08279790699998557, "count": 1, "self": 0.08279790699998557 } } } } } } }