{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4027572870254517, "min": 1.4027572870254517, "max": 1.427780032157898, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70595.1640625, "min": 68856.0234375, "max": 78106.390625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 96.73099415204679, "min": 78.23930269413628, "max": 407.2741935483871, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49623.0, "min": 48893.0, "max": 50502.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999391.0, "min": 49876.0, "max": 1999391.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999391.0, "min": 49876.0, "max": 1999391.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4515936374664307, "min": 0.1728009432554245, "max": 2.5206942558288574, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1257.66748046875, "min": 21.2545166015625, "max": 1568.6982421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7491199699526407, "min": 1.9327814784961017, "max": 3.999783530458808, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1923.2985445857048, "min": 237.73212185502052, "max": 2449.1180480122566, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7491199699526407, "min": 1.9327814784961017, "max": 3.999783530458808, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1923.2985445857048, "min": 237.73212185502052, "max": 2449.1180480122566, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017618502452240944, "min": 0.013663441059361504, "max": 0.02183849867239284, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052855507356722835, "min": 0.027326882118723007, "max": 0.06103125353644524, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04952865118781726, "min": 0.021981656520317, "max": 0.06329379342496395, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.14858595356345178, "min": 0.043963313040634, "max": 0.1727867528796196, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.853948715383337e-06, "min": 3.853948715383337e-06, "max": 0.00029535495154834994, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1561846146150012e-05, "min": 1.1561846146150012e-05, "max": 0.0008441524686158498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10128461666666666, "min": 0.10128461666666666, "max": 0.19845165, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30385385, "min": 0.20773155000000004, "max": 0.5813841500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.410237166666671e-05, "min": 7.410237166666671e-05, "max": 0.004922737335000002, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022230711500000012, "min": 0.00022230711500000012, "max": 0.014071069085000002, "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": "1716399666", "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=Huggy2 --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.3.0+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1716404193" }, "total": 4526.723953975999, "count": 1, "self": 0.5959071849993052, "children": { "run_training.setup": { "total": 0.0675113379998038, "count": 1, "self": 0.0675113379998038 }, "TrainerController.start_learning": { "total": 4526.060535453, "count": 1, "self": 7.63398954602053, "children": { "TrainerController._reset_env": { "total": 3.3568048080001063, "count": 1, "self": 3.3568048080001063 }, "TrainerController.advance": { "total": 4514.94292058998, "count": 232932, "self": 8.275401797624, "children": { "env_step": { "total": 2861.262058828325, "count": 232932, "self": 2383.2211861924557, "children": { "SubprocessEnvManager._take_step": { "total": 473.06625181589743, "count": 232932, "self": 27.83268196595236, "children": { "TorchPolicy.evaluate": { "total": 445.23356984994507, "count": 222988, "self": 445.23356984994507 } } }, "workers": { "total": 4.974620819971733, "count": 232932, "self": 0.0, "children": { "worker_root": { "total": 4513.795769043862, "count": 232932, "is_parallel": true, "self": 2619.8172148297404, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010233900002276641, "count": 1, "is_parallel": true, "self": 0.00026488000048630056, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007585099997413636, "count": 2, "is_parallel": true, "self": 0.0007585099997413636 } } }, "UnityEnvironment.step": { "total": 0.035876520999863715, "count": 1, "is_parallel": true, "self": 0.0004525609997472202, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023819700027161161, "count": 1, "is_parallel": true, "self": 0.00023819700027161161 }, "communicator.exchange": { "total": 0.03432781999981671, "count": 1, "is_parallel": true, "self": 0.03432781999981671 }, "steps_from_proto": { "total": 0.0008579430000281718, "count": 1, "is_parallel": true, "self": 0.00023151600044002407, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006264269995881477, "count": 2, "is_parallel": true, "self": 0.0006264269995881477 } } } } } } }, "UnityEnvironment.step": { "total": 1893.9785542141212, "count": 232931, "is_parallel": true, "self": 59.26188882641918, "children": { "UnityEnvironment._generate_step_input": { "total": 106.63071614285536, "count": 232931, "is_parallel": true, "self": 106.63071614285536 }, "communicator.exchange": { "total": 1596.567126684875, "count": 232931, "is_parallel": true, "self": 1596.567126684875 }, "steps_from_proto": { "total": 131.5188225599718, "count": 232931, "is_parallel": true, "self": 43.02503327660634, "children": { "_process_rank_one_or_two_observation": { "total": 88.49378928336546, "count": 465862, "is_parallel": true, "self": 88.49378928336546 } } } } } } } } } } }, "trainer_advance": { "total": 1645.4054599640308, "count": 232932, "self": 11.720428142406035, "children": { "process_trajectory": { "total": 251.25816185461872, "count": 232932, "self": 249.95070362361912, "children": { "RLTrainer._checkpoint": { "total": 1.3074582309996003, "count": 10, "self": 1.3074582309996003 } } }, "_update_policy": { "total": 1382.426869967006, "count": 97, "self": 328.81809992397893, "children": { "TorchPPOOptimizer.update": { "total": 1053.608770043027, "count": 2910, "self": 1053.608770043027 } } } } } } }, "trainer_threads": { "total": 1.2119999155402184e-06, "count": 1, "self": 1.2119999155402184e-06 }, "TrainerController._save_models": { "total": 0.12681929700011096, "count": 1, "self": 0.004398011999910523, "children": { "RLTrainer._checkpoint": { "total": 0.12242128500020044, "count": 1, "self": 0.12242128500020044 } } } } } } }