{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4071006774902344, "min": 1.4071006774902344, "max": 1.4252249002456665, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72149.0859375, "min": 68196.109375, "max": 77134.3515625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 101.31901840490798, "min": 85.20034843205575, "max": 389.6328125, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49545.0, "min": 48905.0, "max": 49937.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999999.0, "min": 49592.0, "max": 1999999.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999999.0, "min": 49592.0, "max": 1999999.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4003632068634033, "min": 0.07246324419975281, "max": 2.4300596714019775, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1173.777587890625, "min": 9.202832221984863, "max": 1377.1552734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.712686002010704, "min": 1.8805435478217958, "max": 3.942227596918394, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1815.5034549832344, "min": 238.82903057336807, "max": 2208.3265323638916, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.712686002010704, "min": 1.8805435478217958, "max": 3.942227596918394, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1815.5034549832344, "min": 238.82903057336807, "max": 2208.3265323638916, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015514359469671035, "min": 0.01417723047925392, "max": 0.019013413285332112, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.0465430784090131, "min": 0.02835446095850784, "max": 0.056902347716580454, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05276792873111036, "min": 0.02264248017842571, "max": 0.06712562876443068, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15830378619333108, "min": 0.04528496035685142, "max": 0.20137688629329203, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.380198873300008e-06, "min": 3.380198873300008e-06, "max": 0.00029532772655742497, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0140596619900024e-05, "min": 1.0140596619900024e-05, "max": 0.0008440107186631, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10112670000000006, "min": 0.10112670000000006, "max": 0.198442575, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30338010000000015, "min": 0.20739875, "max": 0.5813368999999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.622233000000014e-05, "min": 6.622233000000014e-05, "max": 0.0049222844925, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0001986669900000004, "min": 0.0001986669900000004, "max": 0.014068711309999997, "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": "1715244516", "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": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1715247201" }, "total": 2684.615666952, "count": 1, "self": 0.4442276310005582, "children": { "run_training.setup": { "total": 0.0588998770000444, "count": 1, "self": 0.0588998770000444 }, "TrainerController.start_learning": { "total": 2684.1125394439996, "count": 1, "self": 5.04603352791446, "children": { "TrainerController._reset_env": { "total": 2.9728816319999396, "count": 1, "self": 2.9728816319999396 }, "TrainerController.advance": { "total": 2675.963379316085, "count": 231847, "self": 5.1417496771828155, "children": { "env_step": { "total": 2117.6343093919418, "count": 231847, "self": 1747.8142773649429, "children": { "SubprocessEnvManager._take_step": { "total": 366.46759162198566, "count": 231847, "self": 19.634553456936942, "children": { "TorchPolicy.evaluate": { "total": 346.8330381650487, "count": 223060, "self": 346.8330381650487 } } }, "workers": { "total": 3.352440405013226, "count": 231847, "self": 0.0, "children": { "worker_root": { "total": 2675.872479865059, "count": 231847, "is_parallel": true, "self": 1277.447215706045, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009927329999754875, "count": 1, "is_parallel": true, "self": 0.00027720499997485604, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007155280000006314, "count": 2, "is_parallel": true, "self": 0.0007155280000006314 } } }, "UnityEnvironment.step": { "total": 0.033389006999982485, "count": 1, "is_parallel": true, "self": 0.00045012900000074296, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00022642900000846566, "count": 1, "is_parallel": true, "self": 0.00022642900000846566 }, "communicator.exchange": { "total": 0.03185369000004812, "count": 1, "is_parallel": true, "self": 0.03185369000004812 }, "steps_from_proto": { "total": 0.0008587589999251577, "count": 1, "is_parallel": true, "self": 0.00025541399986650504, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006033450000586527, "count": 2, "is_parallel": true, "self": 0.0006033450000586527 } } } } } } }, "UnityEnvironment.step": { "total": 1398.4252641590142, "count": 231846, "is_parallel": true, "self": 41.94379855097827, "children": { "UnityEnvironment._generate_step_input": { "total": 91.25837950100629, "count": 231846, "is_parallel": true, "self": 91.25837950100629 }, "communicator.exchange": { "total": 1165.1105216559477, "count": 231846, "is_parallel": true, "self": 1165.1105216559477 }, "steps_from_proto": { "total": 100.11256445108188, "count": 231846, "is_parallel": true, "self": 37.725186997197056, "children": { "_process_rank_one_or_two_observation": { "total": 62.387377453884824, "count": 463692, "is_parallel": true, "self": 62.387377453884824 } } } } } } } } } } }, "trainer_advance": { "total": 553.1873202469604, "count": 231847, "self": 7.73586976591389, "children": { "process_trajectory": { "total": 172.77832618204718, "count": 231847, "self": 171.2676038590481, "children": { "RLTrainer._checkpoint": { "total": 1.5107223229990723, "count": 10, "self": 1.5107223229990723 } } }, "_update_policy": { "total": 372.67312429899937, "count": 97, "self": 305.0242872619974, "children": { "TorchPPOOptimizer.update": { "total": 67.64883703700195, "count": 2910, "self": 67.64883703700195 } } } } } } }, "trainer_threads": { "total": 9.200002750731073e-07, "count": 1, "self": 9.200002750731073e-07 }, "TrainerController._save_models": { "total": 0.13024404799989497, "count": 1, "self": 0.0022442969998337503, "children": { "RLTrainer._checkpoint": { "total": 0.12799975100006122, "count": 1, "self": 0.12799975100006122 } } } } } } }