{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.410184383392334, "min": 1.410184383392334, "max": 1.4298412799835205, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 71011.2421875, "min": 68878.65625, "max": 77142.71875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 88.47153024911032, "min": 82.82747068676717, "max": 380.87786259541986, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49721.0, "min": 48986.0, "max": 50082.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999539.0, "min": 49994.0, "max": 1999539.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999539.0, "min": 49994.0, "max": 1999539.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4228267669677734, "min": 0.021930774673819542, "max": 2.4399051666259766, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1361.628662109375, "min": 2.8510007858276367, "max": 1443.612060546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.825166541168274, "min": 1.8561856989677137, "max": 3.9634075938567186, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2149.74359613657, "min": 241.30414086580276, "max": 2298.9701787233353, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.825166541168274, "min": 1.8561856989677137, "max": 3.9634075938567186, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2149.74359613657, "min": 241.30414086580276, "max": 2298.9701787233353, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015745177016247502, "min": 0.013259463931672145, "max": 0.019520314950204922, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04723553104874251, "min": 0.02651892786334429, "max": 0.05856094485061476, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054785531552301515, "min": 0.023354924687494834, "max": 0.06256447428216537, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.16435659465690455, "min": 0.04670984937498967, "max": 0.1770067730297645, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.4814988395333345e-06, "min": 3.4814988395333345e-06, "max": 0.0002953851015383, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0444496518600003e-05, "min": 1.0444496518600003e-05, "max": 0.000844452018516, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10116046666666667, "min": 0.10116046666666667, "max": 0.1984617, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3034814, "min": 0.20746195, "max": 0.5814840000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.790728666666668e-05, "min": 6.790728666666668e-05, "max": 0.004923238830000001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020372186000000003, "min": 0.00020372186000000003, "max": 0.0140760516, "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": "1694103160", "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/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --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": "1694105723" }, "total": 2563.13298129, "count": 1, "self": 0.4452762059995621, "children": { "run_training.setup": { "total": 0.042212445000018306, "count": 1, "self": 0.042212445000018306 }, "TrainerController.start_learning": { "total": 2562.645492639, "count": 1, "self": 4.833128802085412, "children": { "TrainerController._reset_env": { "total": 5.4095478429999275, "count": 1, "self": 5.4095478429999275 }, "TrainerController.advance": { "total": 2552.2806635709144, "count": 232288, "self": 5.008788103903498, "children": { "env_step": { "total": 1988.4364145229479, "count": 232288, "self": 1675.0733286189968, "children": { "SubprocessEnvManager._take_step": { "total": 310.20993739694563, "count": 232288, "self": 17.481466851922505, "children": { "TorchPolicy.evaluate": { "total": 292.72847054502313, "count": 222927, "self": 292.72847054502313 } } }, "workers": { "total": 3.153148507005426, "count": 232288, "self": 0.0, "children": { "worker_root": { "total": 2554.4302285249964, "count": 232288, "is_parallel": true, "self": 1187.7128331359304, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010285879999401004, "count": 1, "is_parallel": true, "self": 0.00035328999990724697, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006752980000328535, "count": 2, "is_parallel": true, "self": 0.0006752980000328535 } } }, "UnityEnvironment.step": { "total": 0.02890638899998521, "count": 1, "is_parallel": true, "self": 0.00035939899998993496, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023852200001783785, "count": 1, "is_parallel": true, "self": 0.00023852200001783785 }, "communicator.exchange": { "total": 0.02757240699997965, "count": 1, "is_parallel": true, "self": 0.02757240699997965 }, "steps_from_proto": { "total": 0.0007360609999977896, "count": 1, "is_parallel": true, "self": 0.00021232000005966256, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005237409999381271, "count": 2, "is_parallel": true, "self": 0.0005237409999381271 } } } } } } }, "UnityEnvironment.step": { "total": 1366.717395389066, "count": 232287, "is_parallel": true, "self": 41.171227912982886, "children": { "UnityEnvironment._generate_step_input": { "total": 85.62678674906999, "count": 232287, "is_parallel": true, "self": 85.62678674906999 }, "communicator.exchange": { "total": 1137.558115334965, "count": 232287, "is_parallel": true, "self": 1137.558115334965 }, "steps_from_proto": { "total": 102.36126539204815, "count": 232287, "is_parallel": true, "self": 38.05683014401427, "children": { "_process_rank_one_or_two_observation": { "total": 64.30443524803388, "count": 464574, "is_parallel": true, "self": 64.30443524803388 } } } } } } } } } } }, "trainer_advance": { "total": 558.8354609440631, "count": 232288, "self": 7.198563885099475, "children": { "process_trajectory": { "total": 145.4306407929614, "count": 232288, "self": 144.21558513696164, "children": { "RLTrainer._checkpoint": { "total": 1.2150556559997767, "count": 10, "self": 1.2150556559997767 } } }, "_update_policy": { "total": 406.20625626600224, "count": 97, "self": 345.4972572849862, "children": { "TorchPPOOptimizer.update": { "total": 60.708998981016066, "count": 2910, "self": 60.708998981016066 } } } } } } }, "trainer_threads": { "total": 1.5200002962956205e-06, "count": 1, "self": 1.5200002962956205e-06 }, "TrainerController._save_models": { "total": 0.12215090300014708, "count": 1, "self": 0.002055907999874762, "children": { "RLTrainer._checkpoint": { "total": 0.12009499500027232, "count": 1, "self": 0.12009499500027232 } } } } } } }