{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.404054045677185, "min": 1.404054045677185, "max": 1.4302388429641724, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 68927.8203125, "min": 68927.8203125, "max": 76937.0, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 75.56814701378254, "min": 72.11859443631039, "max": 378.9548872180451, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49346.0, "min": 49225.0, "max": 50401.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999984.0, "min": 49902.0, "max": 1999984.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999984.0, "min": 49902.0, "max": 1999984.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.49520206451416, "min": 0.17263373732566833, "max": 2.5437538623809814, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1629.366943359375, "min": 22.78765296936035, "max": 1720.103515625, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8805519127006005, "min": 1.7855517968083874, "max": 4.0720211967323605, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2534.000398993492, "min": 235.69283717870712, "max": 2687.901395022869, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8805519127006005, "min": 1.7855517968083874, "max": 4.0720211967323605, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2534.000398993492, "min": 235.69283717870712, "max": 2687.901395022869, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01672971808309538, "min": 0.012334201214738036, "max": 0.021467723971970068, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05018915424928613, "min": 0.024668402429476072, "max": 0.055832795983587855, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06141437801222007, "min": 0.021347857266664508, "max": 0.06927410084754229, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1842431340366602, "min": 0.042695714533329016, "max": 0.1942496385425329, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6088487970833383e-06, "min": 3.6088487970833383e-06, "max": 0.0002953299015567, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0826546391250015e-05, "min": 1.0826546391250015e-05, "max": 0.0008441985186005, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10120291666666666, "min": 0.10120291666666666, "max": 0.19844330000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30360875, "min": 0.2075912, "max": 0.5813995000000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.002554166666676e-05, "min": 7.002554166666676e-05, "max": 0.004922320669999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021007662500000025, "min": 0.00021007662500000025, "max": 0.01407183505, "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": "1700925969", "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": "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": "1700928826" }, "total": 2856.941789543, "count": 1, "self": 0.4251501670005382, "children": { "run_training.setup": { "total": 0.0474414440000146, "count": 1, "self": 0.0474414440000146 }, "TrainerController.start_learning": { "total": 2856.4691979319996, "count": 1, "self": 5.505852623030023, "children": { "TrainerController._reset_env": { "total": 10.84697823099998, "count": 1, "self": 10.84697823099998 }, "TrainerController.advance": { "total": 2840.0023026209697, "count": 233168, "self": 5.7055081779440115, "children": { "env_step": { "total": 2252.3567949230946, "count": 233168, "self": 1847.1588239630826, "children": { "SubprocessEnvManager._take_step": { "total": 401.4660860479934, "count": 233168, "self": 19.46604191006395, "children": { "TorchPolicy.evaluate": { "total": 382.0000441379294, "count": 222874, "self": 382.0000441379294 } } }, "workers": { "total": 3.7318849120186997, "count": 233168, "self": 0.0, "children": { "worker_root": { "total": 2847.979587882044, "count": 233168, "is_parallel": true, "self": 1355.8453371219853, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009327010000106384, "count": 1, "is_parallel": true, "self": 0.0002907079998522022, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006419930001584362, "count": 2, "is_parallel": true, "self": 0.0006419930001584362 } } }, "UnityEnvironment.step": { "total": 0.032035880999956134, "count": 1, "is_parallel": true, "self": 0.00032437699985621293, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020292400006383104, "count": 1, "is_parallel": true, "self": 0.00020292400006383104 }, "communicator.exchange": { "total": 0.03070486800004346, "count": 1, "is_parallel": true, "self": 0.03070486800004346 }, "steps_from_proto": { "total": 0.000803711999992629, "count": 1, "is_parallel": true, "self": 0.00021524400006001088, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005884679999326181, "count": 2, "is_parallel": true, "self": 0.0005884679999326181 } } } } } } }, "UnityEnvironment.step": { "total": 1492.1342507600589, "count": 233167, "is_parallel": true, "self": 44.67922488287354, "children": { "UnityEnvironment._generate_step_input": { "total": 97.18154973320623, "count": 233167, "is_parallel": true, "self": 97.18154973320623 }, "communicator.exchange": { "total": 1245.6151380769588, "count": 233167, "is_parallel": true, "self": 1245.6151380769588 }, "steps_from_proto": { "total": 104.65833806702017, "count": 233167, "is_parallel": true, "self": 38.728875457079084, "children": { "_process_rank_one_or_two_observation": { "total": 65.92946260994108, "count": 466334, "is_parallel": true, "self": 65.92946260994108 } } } } } } } } } } }, "trainer_advance": { "total": 581.939999519931, "count": 233168, "self": 8.15995678484046, "children": { "process_trajectory": { "total": 188.44714996409266, "count": 233168, "self": 187.0481030310923, "children": { "RLTrainer._checkpoint": { "total": 1.3990469330003634, "count": 10, "self": 1.3990469330003634 } } }, "_update_policy": { "total": 385.3328927709979, "count": 97, "self": 316.7614724179982, "children": { "TorchPPOOptimizer.update": { "total": 68.57142035299967, "count": 2910, "self": 68.57142035299967 } } } } } } }, "trainer_threads": { "total": 9.88000010693213e-07, "count": 1, "self": 9.88000010693213e-07 }, "TrainerController._save_models": { "total": 0.11406346900002973, "count": 1, "self": 0.0026868540003306407, "children": { "RLTrainer._checkpoint": { "total": 0.11137661499969909, "count": 1, "self": 0.11137661499969909 } } } } } } }