{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4087220430374146, "min": 1.4087220430374146, "max": 1.4309207201004028, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 72211.09375, "min": 68052.78125, "max": 79063.15625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 113.66819221967964, "min": 82.37061769616027, "max": 378.2481203007519, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49673.0, "min": 48924.0, "max": 50307.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999667.0, "min": 49888.0, "max": 1999667.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999667.0, "min": 49888.0, "max": 1999667.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.3122735023498535, "min": 0.08719915896654129, "max": 2.489725112915039, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1010.4635009765625, "min": 11.510289192199707, "max": 1462.227294921875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.289034128598272, "min": 1.903406365238356, "max": 4.0220330803795195, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1437.307914197445, "min": 251.24964021146297, "max": 2320.0726124048233, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.289034128598272, "min": 1.903406365238356, "max": 4.0220330803795195, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1437.307914197445, "min": 251.24964021146297, "max": 2320.0726124048233, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016296097568718124, "min": 0.013430551515193656, "max": 0.01988731540623121, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.04888829270615437, "min": 0.027738672575408903, "max": 0.0568023210609681, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.04286519171049197, "min": 0.021825358426819246, "max": 0.05901639949944284, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1285955751314759, "min": 0.04365071685363849, "max": 0.1770491984983285, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.744048752016662e-06, "min": 3.744048752016662e-06, "max": 0.000295329976556675, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1232146256049986e-05, "min": 1.1232146256049986e-05, "max": 0.0008442612185796, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124798333333333, "min": 0.10124798333333333, "max": 0.198443325, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30374395, "min": 0.2076658, "max": 0.5814203999999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.227436833333327e-05, "min": 7.227436833333327e-05, "max": 0.0049223219175, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.0002168231049999998, "min": 0.0002168231049999998, "max": 0.014072877960000002, "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": "1690747632", "python_version": "3.10.6 (main, May 29 2023, 11:10:38) [GCC 11.3.0]", "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": "1690750025" }, "total": 2392.246164681, "count": 1, "self": 0.4386482440004329, "children": { "run_training.setup": { "total": 0.040454229999966174, "count": 1, "self": 0.040454229999966174 }, "TrainerController.start_learning": { "total": 2391.767062207, "count": 1, "self": 4.437409849998403, "children": { "TrainerController._reset_env": { "total": 5.4540226940000025, "count": 1, "self": 5.4540226940000025 }, "TrainerController.advance": { "total": 2381.7429221970015, "count": 232247, "self": 4.452080078131075, "children": { "env_step": { "total": 1840.4461235179688, "count": 232247, "self": 1554.7942752219776, "children": { "SubprocessEnvManager._take_step": { "total": 282.7812542639837, "count": 232247, "self": 16.594648728951654, "children": { "TorchPolicy.evaluate": { "total": 266.1866055350321, "count": 223242, "self": 266.1866055350321 } } }, "workers": { "total": 2.870594032007432, "count": 232247, "self": 0.0, "children": { "worker_root": { "total": 2384.2015870419, "count": 232247, "is_parallel": true, "self": 1116.0323439869694, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009091869999906521, "count": 1, "is_parallel": true, "self": 0.0002449680000040644, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006642189999865877, "count": 2, "is_parallel": true, "self": 0.0006642189999865877 } } }, "UnityEnvironment.step": { "total": 0.02864654999996219, "count": 1, "is_parallel": true, "self": 0.0003885279999735758, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021970799997461654, "count": 1, "is_parallel": true, "self": 0.00021970799997461654 }, "communicator.exchange": { "total": 0.027336282000021583, "count": 1, "is_parallel": true, "self": 0.027336282000021583 }, "steps_from_proto": { "total": 0.0007020319999924141, "count": 1, "is_parallel": true, "self": 0.00020531299992399, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004967190000684241, "count": 2, "is_parallel": true, "self": 0.0004967190000684241 } } } } } } }, "UnityEnvironment.step": { "total": 1268.1692430549306, "count": 232246, "is_parallel": true, "self": 40.370129454010794, "children": { "UnityEnvironment._generate_step_input": { "total": 80.80360343397962, "count": 232246, "is_parallel": true, "self": 80.80360343397962 }, "communicator.exchange": { "total": 1050.7603942908966, "count": 232246, "is_parallel": true, "self": 1050.7603942908966 }, "steps_from_proto": { "total": 96.23511587604366, "count": 232246, "is_parallel": true, "self": 34.70303503501833, "children": { "_process_rank_one_or_two_observation": { "total": 61.53208084102533, "count": 464492, "is_parallel": true, "self": 61.53208084102533 } } } } } } } } } } }, "trainer_advance": { "total": 536.8447186009016, "count": 232247, "self": 6.448803433045441, "children": { "process_trajectory": { "total": 131.8560732718554, "count": 232247, "self": 130.51097254185515, "children": { "RLTrainer._checkpoint": { "total": 1.3451007300002402, "count": 10, "self": 1.3451007300002402 } } }, "_update_policy": { "total": 398.5398418960007, "count": 97, "self": 339.2824421430089, "children": { "TorchPPOOptimizer.update": { "total": 59.25739975299183, "count": 2910, "self": 59.25739975299183 } } } } } } }, "trainer_threads": { "total": 8.060001164267305e-07, "count": 1, "self": 8.060001164267305e-07 }, "TrainerController._save_models": { "total": 0.13270666000016718, "count": 1, "self": 0.0018746599998848978, "children": { "RLTrainer._checkpoint": { "total": 0.13083200000028228, "count": 1, "self": 0.13083200000028228 } } } } } } }