{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4039725065231323, "min": 1.4039725065231323, "max": 1.4277423620224, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69693.1953125, "min": 69019.640625, "max": 77744.15625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 70.95107913669065, "min": 69.92765957446808, "max": 378.5681818181818, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49311.0, "min": 49214.0, "max": 50066.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999940.0, "min": 49831.0, "max": 1999940.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999940.0, "min": 49831.0, "max": 1999940.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.489853858947754, "min": 0.10592063516378403, "max": 2.5735511779785156, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1730.448486328125, "min": 13.875603675842285, "max": 1753.551025390625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8891523538733557, "min": 1.7246136716531433, "max": 4.128395850863753, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2702.9608859419823, "min": 225.92439098656178, "max": 2733.0869435071945, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8891523538733557, "min": 1.7246136716531433, "max": 4.128395850863753, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2702.9608859419823, "min": 225.92439098656178, "max": 2733.0869435071945, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018041961774179074, "min": 0.014941545078181663, "max": 0.02037012575698706, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05412588532253722, "min": 0.029883090156363326, "max": 0.05742798411132147, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06604799268146357, "min": 0.02276067603379488, "max": 0.06604799268146357, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.19814397804439068, "min": 0.04552135206758976, "max": 0.19814397804439068, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.646398784566679e-06, "min": 3.646398784566679e-06, "max": 0.0002953008015663999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0939196353700038e-05, "min": 1.0939196353700038e-05, "max": 0.0008437057687647499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10121543333333334, "min": 0.10121543333333334, "max": 0.19843360000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30364630000000004, "min": 0.2075628, "max": 0.5812352499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.065012333333356e-05, "min": 7.065012333333356e-05, "max": 0.00492183664, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002119503700000007, "min": 0.0002119503700000007, "max": 0.014063638975, "count": 40 }, "Huggy.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 }, "Huggy.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 40 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1705132792", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1705138079" }, "total": 5287.190682804, "count": 1, "self": 0.6040964459998577, "children": { "run_training.setup": { "total": 0.10981935700010581, "count": 1, "self": 0.10981935700010581 }, "TrainerController.start_learning": { "total": 5286.476767001001, "count": 1, "self": 10.119755968114987, "children": { "TrainerController._reset_env": { "total": 5.773866148999787, "count": 1, "self": 5.773866148999787 }, "TrainerController.advance": { "total": 5270.437490008887, "count": 233233, "self": 9.723547940583558, "children": { "env_step": { "total": 3441.9826717462543, "count": 233233, "self": 2859.8953009492357, "children": { "SubprocessEnvManager._take_step": { "total": 575.3883779180069, "count": 233233, "self": 36.99826363675356, "children": { "TorchPolicy.evaluate": { "total": 538.3901142812533, "count": 222892, "self": 538.3901142812533 } } }, "workers": { "total": 6.698992879011712, "count": 233233, "self": 0.0, "children": { "worker_root": { "total": 5269.789646990998, "count": 233233, "is_parallel": true, "self": 2984.930481082909, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0012242940001669922, "count": 1, "is_parallel": true, "self": 0.0004120600005990127, "children": { "_process_rank_one_or_two_observation": { "total": 0.0008122339995679795, "count": 2, "is_parallel": true, "self": 0.0008122339995679795 } } }, "UnityEnvironment.step": { "total": 0.039620354999897245, "count": 1, "is_parallel": true, "self": 0.0004492399998525798, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00025224199998774566, "count": 1, "is_parallel": true, "self": 0.00025224199998774566 }, "communicator.exchange": { "total": 0.037938205000045855, "count": 1, "is_parallel": true, "self": 0.037938205000045855 }, "steps_from_proto": { "total": 0.0009806680000110646, "count": 1, "is_parallel": true, "self": 0.00025273400024161674, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007279339997694478, "count": 2, "is_parallel": true, "self": 0.0007279339997694478 } } } } } } }, "UnityEnvironment.step": { "total": 2284.8591659080894, "count": 233232, "is_parallel": true, "self": 72.25854080093131, "children": { "UnityEnvironment._generate_step_input": { "total": 107.02569216110533, "count": 233232, "is_parallel": true, "self": 107.02569216110533 }, "communicator.exchange": { "total": 1952.1614315679276, "count": 233232, "is_parallel": true, "self": 1952.1614315679276 }, "steps_from_proto": { "total": 153.41350137812515, "count": 233232, "is_parallel": true, "self": 47.65565394304258, "children": { "_process_rank_one_or_two_observation": { "total": 105.75784743508257, "count": 466464, "is_parallel": true, "self": 105.75784743508257 } } } } } } } } } } }, "trainer_advance": { "total": 1818.731270322049, "count": 233233, "self": 15.98783205067275, "children": { "process_trajectory": { "total": 302.3439428153729, "count": 233233, "self": 300.8415513873738, "children": { "RLTrainer._checkpoint": { "total": 1.5023914279991004, "count": 10, "self": 1.5023914279991004 } } }, "_update_policy": { "total": 1500.3994954560035, "count": 97, "self": 381.3595048289844, "children": { "TorchPPOOptimizer.update": { "total": 1119.039990627019, "count": 2910, "self": 1119.039990627019 } } } } } } }, "trainer_threads": { "total": 1.1969996194238774e-06, "count": 1, "self": 1.1969996194238774e-06 }, "TrainerController._save_models": { "total": 0.14565367799968953, "count": 1, "self": 0.004367424999145442, "children": { "RLTrainer._checkpoint": { "total": 0.1412862530005441, "count": 1, "self": 0.1412862530005441 } } } } } } }