{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4076870679855347, "min": 1.4076870679855347, "max": 1.430122971534729, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69045.640625, "min": 68172.8046875, "max": 76708.3671875, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 105.76709401709402, "min": 94.15719696969697, "max": 372.5149253731343, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49499.0, "min": 49028.0, "max": 50019.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999969.0, "min": 49777.0, "max": 1999969.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999969.0, "min": 49777.0, "max": 1999969.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.337676763534546, "min": 0.23268161714076996, "max": 2.3831870555877686, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1094.03271484375, "min": 30.9466552734375, "max": 1253.18115234375, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.635354549711586, "min": 1.8188588377228356, "max": 3.8406053235471385, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 1701.3459292650223, "min": 241.90822541713715, "max": 1950.3235466480255, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.635354549711586, "min": 1.8188588377228356, "max": 3.8406053235471385, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 1701.3459292650223, "min": 241.90822541713715, "max": 1950.3235466480255, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.01581071741799557, "min": 0.014126499366446095, "max": 0.01977496241258147, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.03162143483599114, "min": 0.02865908739428657, "max": 0.05707283400697634, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.050606238593657815, "min": 0.020078918213645616, "max": 0.05571669364968936, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.10121247718731563, "min": 0.04015783642729123, "max": 0.16715008094906808, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 4.46582351142501e-06, "min": 4.46582351142501e-06, "max": 0.00029536095154635, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 8.93164702285002e-06, "min": 8.93164702285002e-06, "max": 0.0008440882686372498, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10148857499999997, "min": 0.10148857499999997, "max": 0.19845364999999995, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.20297714999999994, "min": 0.20297714999999994, "max": 0.5813627499999998, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 8.427989250000016e-05, "min": 8.427989250000016e-05, "max": 0.004922837135, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00016855978500000032, "min": 0.00016855978500000032, "max": 0.014070001225000002, "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": "1714983444", "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=Huggy --no-graphics", "mlagents_version": "1.1.0.dev0", "mlagents_envs_version": "1.1.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.2.1+cu121", "numpy_version": "1.23.5", "end_time_seconds": "1714985851" }, "total": 2406.5864913960004, "count": 1, "self": 0.4380099180002617, "children": { "run_training.setup": { "total": 0.06135000599999785, "count": 1, "self": 0.06135000599999785 }, "TrainerController.start_learning": { "total": 2406.0871314720002, "count": 1, "self": 4.294789541010687, "children": { "TrainerController._reset_env": { "total": 3.4913513280000075, "count": 1, "self": 3.4913513280000075 }, "TrainerController.advance": { "total": 2398.1850391239896, "count": 231323, "self": 4.914551738983846, "children": { "env_step": { "total": 1905.3285520899776, "count": 231323, "self": 1584.2683770449012, "children": { "SubprocessEnvManager._take_step": { "total": 318.15198712497005, "count": 231323, "self": 16.358768192912635, "children": { "TorchPolicy.evaluate": { "total": 301.7932189320574, "count": 222904, "self": 301.7932189320574 } } }, "workers": { "total": 2.9081879201065135, "count": 231323, "self": 0.0, "children": { "worker_root": { "total": 2398.709726397107, "count": 231323, "is_parallel": true, "self": 1122.0304958041143, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.000950009999996837, "count": 1, "is_parallel": true, "self": 0.00023900000002186061, "children": { "_process_rank_one_or_two_observation": { "total": 0.0007110099999749764, "count": 2, "is_parallel": true, "self": 0.0007110099999749764 } } }, "UnityEnvironment.step": { "total": 0.02975845200001004, "count": 1, "is_parallel": true, "self": 0.00038328199991610745, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00021494899999652262, "count": 1, "is_parallel": true, "self": 0.00021494899999652262 }, "communicator.exchange": { "total": 0.02841784400004599, "count": 1, "is_parallel": true, "self": 0.02841784400004599 }, "steps_from_proto": { "total": 0.0007423770000514196, "count": 1, "is_parallel": true, "self": 0.0001912640000796273, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005511129999717923, "count": 2, "is_parallel": true, "self": 0.0005511129999717923 } } } } } } }, "UnityEnvironment.step": { "total": 1276.6792305929926, "count": 231322, "is_parallel": true, "self": 39.39054608201013, "children": { "UnityEnvironment._generate_step_input": { "total": 82.59121431089847, "count": 231322, "is_parallel": true, "self": 82.59121431089847 }, "communicator.exchange": { "total": 1062.6122742190526, "count": 231322, "is_parallel": true, "self": 1062.6122742190526 }, "steps_from_proto": { "total": 92.08519598103123, "count": 231322, "is_parallel": true, "self": 33.147538016991234, "children": { "_process_rank_one_or_two_observation": { "total": 58.93765796404, "count": 462644, "is_parallel": true, "self": 58.93765796404 } } } } } } } } } } }, "trainer_advance": { "total": 487.9419352950282, "count": 231323, "self": 6.575800512020976, "children": { "process_trajectory": { "total": 150.42956683000835, "count": 231323, "self": 149.13416843200804, "children": { "RLTrainer._checkpoint": { "total": 1.2953983980003159, "count": 10, "self": 1.2953983980003159 } } }, "_update_policy": { "total": 330.93656795299887, "count": 96, "self": 267.47149998000424, "children": { "TorchPPOOptimizer.update": { "total": 63.46506797299463, "count": 2880, "self": 63.46506797299463 } } } } } } }, "trainer_threads": { "total": 9.37000095291296e-07, "count": 1, "self": 9.37000095291296e-07 }, "TrainerController._save_models": { "total": 0.11595054200006416, "count": 1, "self": 0.0023582869998790557, "children": { "RLTrainer._checkpoint": { "total": 0.1135922550001851, "count": 1, "self": 0.1135922550001851 } } } } } } }