{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4053928852081299, "min": 1.4053744077682495, "max": 1.427560567855835, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69238.0859375, "min": 69184.515625, "max": 77934.3046875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 80.61500815660685, "min": 76.14506172839506, "max": 370.94074074074075, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49417.0, "min": 49261.0, "max": 50077.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999978.0, "min": 49744.0, "max": 1999978.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999978.0, "min": 49744.0, "max": 1999978.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4924492835998535, "min": 0.12894751131534576, "max": 2.538984537124634, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1527.871337890625, "min": 17.278966903686523, "max": 1610.322998046875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.787694534022501, "min": 1.9671334106085905, "max": 4.017099762393531, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2321.856749355793, "min": 263.59587702155113, "max": 2492.0886703133583, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.787694534022501, "min": 1.9671334106085905, "max": 4.017099762393531, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2321.856749355793, "min": 263.59587702155113, "max": 2492.0886703133583, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01722113557754912, "min": 0.012949757452709794, "max": 0.01978959573219375, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05166340673264736, "min": 0.02589951490541959, "max": 0.05544828856751943, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0690692003402445, "min": 0.021194356959313154, "max": 0.07007818563530843, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.2072076010207335, "min": 0.04238871391862631, "max": 0.2072076010207335, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.5238488254166695e-06, "min": 3.5238488254166695e-06, "max": 0.00029533822655392495, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0571546476250009e-05, "min": 1.0571546476250009e-05, "max": 0.0008439181686939499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117458333333335, "min": 0.10117458333333335, "max": 0.19844607500000006, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30352375000000004, "min": 0.20748394999999997, "max": 0.5813060500000002, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.86117083333334e-05, "min": 6.86117083333334e-05, "max": 0.0049224591425, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002058351250000002, "min": 0.0002058351250000002, "max": 0.014067171895000001, "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": "1671626818", "python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", "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": "0.29.0.dev0", "mlagents_envs_version": "0.29.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "1.8.1+cu102", "numpy_version": "1.21.6", "end_time_seconds": "1671628999" }, "total": 2181.257631171, "count": 1, "self": 0.3927918009999303, "children": { "run_training.setup": { "total": 0.10415701499994157, "count": 1, "self": 0.10415701499994157 }, "TrainerController.start_learning": { "total": 2180.760682355, "count": 1, "self": 3.7507646620083506, "children": { "TrainerController._reset_env": { "total": 7.765974740999923, "count": 1, "self": 7.765974740999923 }, "TrainerController.advance": { "total": 2169.1246787119917, "count": 232979, "self": 3.983323234972886, "children": { "env_step": { "total": 1702.2777183799863, "count": 232979, "self": 1433.0372745650238, "children": { "SubprocessEnvManager._take_step": { "total": 266.76652796803637, "count": 232979, "self": 14.06378879609133, "children": { "TorchPolicy.evaluate": { "total": 252.70273917194504, "count": 222926, "self": 63.07405114589142, "children": { "TorchPolicy.sample_actions": { "total": 189.62868802605362, "count": 222926, "self": 189.62868802605362 } } } } }, "workers": { "total": 2.473915846926161, "count": 232979, "self": 0.0, "children": { "worker_root": { "total": 2173.337774735024, "count": 232979, "is_parallel": true, "self": 989.022727003002, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.002163786999972217, "count": 1, "is_parallel": true, "self": 0.0003493619998380382, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018144250001341788, "count": 2, "is_parallel": true, "self": 0.0018144250001341788 } } }, "UnityEnvironment.step": { "total": 0.027963095000018257, "count": 1, "is_parallel": true, "self": 0.0002615370000285111, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019326899996485736, "count": 1, "is_parallel": true, "self": 0.00019326899996485736 }, "communicator.exchange": { "total": 0.026801915000078225, "count": 1, "is_parallel": true, "self": 0.026801915000078225 }, "steps_from_proto": { "total": 0.0007063739999466634, "count": 1, "is_parallel": true, "self": 0.00023619700004928745, "children": { "_process_rank_one_or_two_observation": { "total": 0.00047017699989737594, "count": 2, "is_parallel": true, "self": 0.00047017699989737594 } } } } } } }, "UnityEnvironment.step": { "total": 1184.315047732022, "count": 232978, "is_parallel": true, "self": 34.40734493294917, "children": { "UnityEnvironment._generate_step_input": { "total": 75.50309094604154, "count": 232978, "is_parallel": true, "self": 75.50309094604154 }, "communicator.exchange": { "total": 982.1065627679458, "count": 232978, "is_parallel": true, "self": 982.1065627679458 }, "steps_from_proto": { "total": 92.29804908508561, "count": 232978, "is_parallel": true, "self": 37.830861272284665, "children": { "_process_rank_one_or_two_observation": { "total": 54.467187812800944, "count": 465956, "is_parallel": true, "self": 54.467187812800944 } } } } } } } } } } }, "trainer_advance": { "total": 462.86363709703267, "count": 232979, "self": 5.649200087051781, "children": { "process_trajectory": { "total": 148.2189481359801, "count": 232979, "self": 147.05933352098032, "children": { "RLTrainer._checkpoint": { "total": 1.1596146149997821, "count": 10, "self": 1.1596146149997821 } } }, "_update_policy": { "total": 308.9954888740008, "count": 97, "self": 256.6239334890047, "children": { "TorchPPOOptimizer.update": { "total": 52.3715553849961, "count": 2910, "self": 52.3715553849961 } } } } } } }, "trainer_threads": { "total": 9.149998732027598e-07, "count": 1, "self": 9.149998732027598e-07 }, "TrainerController._save_models": { "total": 0.11926332500024728, "count": 1, "self": 0.0027428950006651576, "children": { "RLTrainer._checkpoint": { "total": 0.11652042999958212, "count": 1, "self": 0.11652042999958212 } } } } } } }