{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4089703559875488, "min": 1.4089703559875488, "max": 1.427398443222046, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70950.109375, "min": 69469.859375, "max": 74877.734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 77.74203821656052, "min": 76.51007751937985, "max": 400.608, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48822.0, "min": 48773.0, "max": 50102.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999930.0, "min": 49919.0, "max": 1999930.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999930.0, "min": 49919.0, "max": 1999930.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4311015605926514, "min": 0.07589166611433029, "max": 2.5304577350616455, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1526.7318115234375, "min": 9.410566329956055, "max": 1593.5150146484375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.741109391686263, "min": 1.8814829925615941, "max": 4.086356966763881, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2349.4166979789734, "min": 233.30389107763767, "max": 2516.2895206809044, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.741109391686263, "min": 1.8814829925615941, "max": 4.086356966763881, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2349.4166979789734, "min": 233.30389107763767, "max": 2516.2895206809044, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016584009950424337, "min": 0.012913032733194996, "max": 0.020405270324535728, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.049752029851273014, "min": 0.02728188410013293, "max": 0.059039400903081206, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.054067076535688506, "min": 0.022659460734575986, "max": 0.06291939932852983, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1622012296070655, "min": 0.04531892146915197, "max": 0.18478935658931733, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6942487686166735e-06, "min": 3.6942487686166735e-06, "max": 0.000295295926568025, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.108274630585002e-05, "min": 1.108274630585002e-05, "max": 0.0008439634686788499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10123138333333336, "min": 0.10123138333333336, "max": 0.19843197500000004, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30369415000000005, "min": 0.20758885, "max": 0.58132115, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.144602833333346e-05, "min": 7.144602833333346e-05, "max": 0.0049217555525000005, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021433808500000037, "min": 0.00021433808500000037, "max": 0.014067925384999999, "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": "1671095562", "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": "1671097775" }, "total": 2212.6267312210002, "count": 1, "self": 0.38923340300016207, "children": { "run_training.setup": { "total": 0.10331395600002224, "count": 1, "self": 0.10331395600002224 }, "TrainerController.start_learning": { "total": 2212.134183862, "count": 1, "self": 3.859601093958645, "children": { "TrainerController._reset_env": { "total": 11.18641736699999, "count": 1, "self": 11.18641736699999 }, "TrainerController.advance": { "total": 2196.973276620042, "count": 232969, "self": 4.033624010995936, "children": { "env_step": { "total": 1730.3680932470274, "count": 232969, "self": 1454.3027725630172, "children": { "SubprocessEnvManager._take_step": { "total": 273.50197372402636, "count": 232969, "self": 14.747057445029213, "children": { "TorchPolicy.evaluate": { "total": 258.75491627899714, "count": 223014, "self": 65.46415880402293, "children": { "TorchPolicy.sample_actions": { "total": 193.2907574749742, "count": 223014, "self": 193.2907574749742 } } } } }, "workers": { "total": 2.5633469599837326, "count": 232969, "self": 0.0, "children": { "worker_root": { "total": 2204.2624310570354, "count": 232969, "is_parallel": true, "self": 1009.9970824390039, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0021365290000403547, "count": 1, "is_parallel": true, "self": 0.00029489700000340235, "children": { "_process_rank_one_or_two_observation": { "total": 0.0018416320000369524, "count": 2, "is_parallel": true, "self": 0.0018416320000369524 } } }, "UnityEnvironment.step": { "total": 0.026965529999984028, "count": 1, "is_parallel": true, "self": 0.0002774039999735578, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0002341829999750189, "count": 1, "is_parallel": true, "self": 0.0002341829999750189 }, "communicator.exchange": { "total": 0.02573839400002953, "count": 1, "is_parallel": true, "self": 0.02573839400002953 }, "steps_from_proto": { "total": 0.0007155490000059217, "count": 1, "is_parallel": true, "self": 0.00025368500001832217, "children": { "_process_rank_one_or_two_observation": { "total": 0.00046186399998759953, "count": 2, "is_parallel": true, "self": 0.00046186399998759953 } } } } } } }, "UnityEnvironment.step": { "total": 1194.2653486180316, "count": 232968, "is_parallel": true, "self": 34.41186618999063, "children": { "UnityEnvironment._generate_step_input": { "total": 76.40932285094533, "count": 232968, "is_parallel": true, "self": 76.40932285094533 }, "communicator.exchange": { "total": 988.8332328471058, "count": 232968, "is_parallel": true, "self": 988.8332328471058 }, "steps_from_proto": { "total": 94.61092672998984, "count": 232968, "is_parallel": true, "self": 40.66617012004315, "children": { "_process_rank_one_or_two_observation": { "total": 53.944756609946694, "count": 465936, "is_parallel": true, "self": 53.944756609946694 } } } } } } } } } } }, "trainer_advance": { "total": 462.5715593620185, "count": 232969, "self": 6.21997825603205, "children": { "process_trajectory": { "total": 150.52007339198764, "count": 232969, "self": 149.36789059698827, "children": { "RLTrainer._checkpoint": { "total": 1.1521827949993622, "count": 10, "self": 1.1521827949993622 } } }, "_update_policy": { "total": 305.8315077139988, "count": 97, "self": 253.06064114000208, "children": { "TorchPPOOptimizer.update": { "total": 52.77086657399673, "count": 2910, "self": 52.77086657399673 } } } } } } }, "trainer_threads": { "total": 1.5949999578879215e-06, "count": 1, "self": 1.5949999578879215e-06 }, "TrainerController._save_models": { "total": 0.11488718599957792, "count": 1, "self": 0.0021613829994748812, "children": { "RLTrainer._checkpoint": { "total": 0.11272580300010304, "count": 1, "self": 0.11272580300010304 } } } } } } }