{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4043039083480835, "min": 1.4043039083480835, "max": 1.4269198179244995, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69497.59375, "min": 68023.5625, "max": 76656.6640625, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 92.13035381750466, "min": 80.01132686084142, "max": 422.9406779661017, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49474.0, "min": 48842.0, "max": 50278.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999949.0, "min": 49398.0, "max": 1999949.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999949.0, "min": 49398.0, "max": 1999949.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.431154727935791, "min": 0.250816285610199, "max": 2.505901575088501, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1305.530029296875, "min": 29.34550666809082, "max": 1523.94677734375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.739315111099897, "min": 1.7785874230739398, "max": 4.0416845998173345, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2008.0122146606445, "min": 208.09472849965096, "max": 2423.1629583239555, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.739315111099897, "min": 1.7785874230739398, "max": 4.0416845998173345, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2008.0122146606445, "min": 208.09472849965096, "max": 2423.1629583239555, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01732831451954553, "min": 0.013319832148530015, "max": 0.020035931631961525, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05198494355863659, "min": 0.02663966429706003, "max": 0.058812583861678536, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.051211183725131885, "min": 0.01880707290644447, "max": 0.05671035430083672, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.15363355117539565, "min": 0.03761414581288894, "max": 0.16453388382991155, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.945598684833335e-06, "min": 3.945598684833335e-06, "max": 0.0002953617015460999, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1836796054500005e-05, "min": 1.1836796054500005e-05, "max": 0.0008443021685659499, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10131516666666666, "min": 0.10131516666666666, "max": 0.19845390000000002, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3039455, "min": 0.20776180000000005, "max": 0.5814340499999999, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.562681666666672e-05, "min": 7.562681666666672e-05, "max": 0.00492284961, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00022688045000000015, "min": 0.00022688045000000015, "max": 0.014073559095, "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": "1697629042", "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": "2.0.1+cu118", "numpy_version": "1.23.5", "end_time_seconds": "1697631693" }, "total": 2651.0820273010004, "count": 1, "self": 0.47588725700052237, "children": { "run_training.setup": { "total": 0.05974654999999984, "count": 1, "self": 0.05974654999999984 }, "TrainerController.start_learning": { "total": 2650.546393494, "count": 1, "self": 5.046475003001888, "children": { "TrainerController._reset_env": { "total": 8.534825740999963, "count": 1, "self": 8.534825740999963 }, "TrainerController.advance": { "total": 2636.8434954159984, "count": 232818, "self": 5.130324603039298, "children": { "env_step": { "total": 2071.9516180779847, "count": 232818, "self": 1720.3628545819531, "children": { "SubprocessEnvManager._take_step": { "total": 348.34496510197147, "count": 232818, "self": 17.74272595695936, "children": { "TorchPolicy.evaluate": { "total": 330.6022391450121, "count": 223008, "self": 330.6022391450121 } } }, "workers": { "total": 3.243798394060036, "count": 232818, "self": 0.0, "children": { "worker_root": { "total": 2642.5386796889475, "count": 232818, "is_parallel": true, "self": 1242.1905187729267, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008661310000093181, "count": 1, "is_parallel": true, "self": 0.0002445549999379182, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006215760000713999, "count": 2, "is_parallel": true, "self": 0.0006215760000713999 } } }, "UnityEnvironment.step": { "total": 0.0337183070000151, "count": 1, "is_parallel": true, "self": 0.0003473050000479816, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020965599998135076, "count": 1, "is_parallel": true, "self": 0.00020965599998135076 }, "communicator.exchange": { "total": 0.03234356299998353, "count": 1, "is_parallel": true, "self": 0.03234356299998353 }, "steps_from_proto": { "total": 0.0008177830000022368, "count": 1, "is_parallel": true, "self": 0.00023454900002661816, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005832339999756186, "count": 2, "is_parallel": true, "self": 0.0005832339999756186 } } } } } } }, "UnityEnvironment.step": { "total": 1400.3481609160208, "count": 232817, "is_parallel": true, "self": 43.96076600090555, "children": { "UnityEnvironment._generate_step_input": { "total": 88.88730002198565, "count": 232817, "is_parallel": true, "self": 88.88730002198565 }, "communicator.exchange": { "total": 1169.0094963231054, "count": 232817, "is_parallel": true, "self": 1169.0094963231054 }, "steps_from_proto": { "total": 98.4905985700243, "count": 232817, "is_parallel": true, "self": 34.632135139001036, "children": { "_process_rank_one_or_two_observation": { "total": 63.85846343102327, "count": 465634, "is_parallel": true, "self": 63.85846343102327 } } } } } } } } } } }, "trainer_advance": { "total": 559.7615527349745, "count": 232818, "self": 7.354427379993581, "children": { "process_trajectory": { "total": 163.69257924098042, "count": 232818, "self": 162.39496871498056, "children": { "RLTrainer._checkpoint": { "total": 1.2976105259998576, "count": 10, "self": 1.2976105259998576 } } }, "_update_policy": { "total": 388.71454611400054, "count": 97, "self": 321.03438176200007, "children": { "TorchPPOOptimizer.update": { "total": 67.68016435200047, "count": 2910, "self": 67.68016435200047 } } } } } } }, "trainer_threads": { "total": 1.4899997040629387e-06, "count": 1, "self": 1.4899997040629387e-06 }, "TrainerController._save_models": { "total": 0.12159584399978485, "count": 1, "self": 0.0021603179998237465, "children": { "RLTrainer._checkpoint": { "total": 0.1194355259999611, "count": 1, "self": 0.1194355259999611 } } } } } } }