{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.8055532574653625, "min": 0.7974890470504761, "max": 2.8554625511169434, "count": 30 }, "SnowballTarget.Policy.Entropy.sum": { "value": 8276.25390625, "min": 7855.34912109375, "max": 29242.79296875, "count": 30 }, "SnowballTarget.Step.mean": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Step.sum": { "value": 299968.0, "min": 9952.0, "max": 299968.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 13.26636028289795, "min": 0.2261212319135666, "max": 13.26636028289795, "count": 30 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2706.33740234375, "min": 43.86751937866211, "max": 2706.33740234375, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 30 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 10945.0, "min": 8756.0, "max": 10945.0, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.07250593102573617, "min": 0.06361447321062716, "max": 0.07608299297092291, "count": 30 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.36252965512868085, "min": 0.25911760008688467, "max": 0.3722585622625261, "count": 30 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.17176396706525016, "min": 0.11877474184125188, "max": 0.2690399873444774, "count": 30 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8588198353262508, "min": 0.4750989673650075, "max": 1.3289753072986414, "count": 30 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 5.288098237333331e-06, "min": 5.288098237333331e-06, "max": 0.00029458800180399996, "count": 30 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 2.6440491186666655e-05, "min": 2.6440491186666655e-05, "max": 0.0014234400255199997, "count": 30 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10176266666666667, "min": 0.10176266666666667, "max": 0.198196, "count": 30 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.5088133333333333, "min": 0.42025066666666666, "max": 0.97448, "count": 30 }, "SnowballTarget.Policy.Beta.mean": { "value": 9.795706666666662e-05, "min": 9.795706666666662e-05, "max": 0.0049099804000000006, "count": 30 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0004897853333333331, "min": 0.0004897853333333331, "max": 0.023726551999999998, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 26.527272727272727, "min": 3.3181818181818183, "max": 26.527272727272727, "count": 30 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1459.0, "min": 146.0, "max": 1459.0, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 26.527272727272727, "min": 3.3181818181818183, "max": 26.527272727272727, "count": 30 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1459.0, "min": 146.0, "max": 1459.0, "count": 30 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 30 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1702880232", "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/config.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": "2.1.2+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1702880891" }, "total": 658.639849972, "count": 1, "self": 0.44870032399990123, "children": { "run_training.setup": { "total": 0.053578917999971054, "count": 1, "self": 0.053578917999971054 }, "TrainerController.start_learning": { "total": 658.1375707300001, "count": 1, "self": 0.814569468999025, "children": { "TrainerController._reset_env": { "total": 3.2650227579999864, "count": 1, "self": 3.2650227579999864 }, "TrainerController.advance": { "total": 653.9684580330011, "count": 27331, "self": 0.3804264520073275, "children": { "env_step": { "total": 653.5880315809937, "count": 27331, "self": 429.71914928598073, "children": { "SubprocessEnvManager._take_step": { "total": 223.45796053300853, "count": 27331, "self": 2.178946096978734, "children": { "TorchPolicy.evaluate": { "total": 221.2790144360298, "count": 27331, "self": 221.2790144360298 } } }, "workers": { "total": 0.4109217620044774, "count": 27331, "self": 0.0, "children": { "worker_root": { "total": 656.4618278449974, "count": 27331, "is_parallel": true, "self": 323.43727517699733, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.003953400000000329, "count": 1, "is_parallel": true, "self": 0.0027398440001888957, "children": { "_process_rank_one_or_two_observation": { "total": 0.0012135559998114331, "count": 10, "is_parallel": true, "self": 0.0012135559998114331 } } }, "UnityEnvironment.step": { "total": 0.03986100899999201, "count": 1, "is_parallel": true, "self": 0.0007084290000420879, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0003714399999807938, "count": 1, "is_parallel": true, "self": 0.0003714399999807938 }, "communicator.exchange": { "total": 0.036644274999957815, "count": 1, "is_parallel": true, "self": 0.036644274999957815 }, "steps_from_proto": { "total": 0.002136865000011312, "count": 1, "is_parallel": true, "self": 0.00041163899982166186, "children": { "_process_rank_one_or_two_observation": { "total": 0.0017252260001896502, "count": 10, "is_parallel": true, "self": 0.0017252260001896502 } } } } } } }, "UnityEnvironment.step": { "total": 333.02455266800007, "count": 27330, "is_parallel": true, "self": 15.749770333011611, "children": { "UnityEnvironment._generate_step_input": { "total": 7.792997897999612, "count": 27330, "is_parallel": true, "self": 7.792997897999612 }, "communicator.exchange": { "total": 260.0691906399935, "count": 27330, "is_parallel": true, "self": 260.0691906399935 }, "steps_from_proto": { "total": 49.41259379699534, "count": 27330, "is_parallel": true, "self": 8.951614119018245, "children": { "_process_rank_one_or_two_observation": { "total": 40.46097967797709, "count": 273300, "is_parallel": true, "self": 40.46097967797709 } } } } } } } } } } } } }, "trainer_threads": { "total": 0.0005022390000704036, "count": 1, "self": 0.0005022390000704036, "children": { "thread_root": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "trainer_advance": { "total": 645.7611521119019, "count": 981309, "is_parallel": true, "self": 20.24979291794807, "children": { "process_trajectory": { "total": 358.4520205749543, "count": 981309, "is_parallel": true, "self": 357.2673775479541, "children": { "RLTrainer._checkpoint": { "total": 1.1846430270002202, "count": 6, "is_parallel": true, "self": 1.1846430270002202 } } }, "_update_policy": { "total": 267.0593386189995, "count": 136, "is_parallel": true, "self": 82.45793512799833, "children": { "TorchPPOOptimizer.update": { "total": 184.60140349100118, "count": 6930, "is_parallel": true, "self": 184.60140349100118 } } } } } } } } }, "TrainerController._save_models": { "total": 0.08901823099995454, "count": 1, "self": 0.001042293999944377, "children": { "RLTrainer._checkpoint": { "total": 0.08797593700001016, "count": 1, "self": 0.08797593700001016 } } } } } } }