{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.410109519958496, "min": 1.410109519958496, "max": 1.430841326713562, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69318.1640625, "min": 69318.1640625, "max": 76570.2734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 76.64596273291926, "min": 73.75186846038864, "max": 388.47286821705427, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49360.0, "min": 48797.0, "max": 50113.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999935.0, "min": 49515.0, "max": 1999935.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999935.0, "min": 49515.0, "max": 1999935.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.5197486877441406, "min": 0.06916273385286331, "max": 2.557778835296631, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1622.7181396484375, "min": 8.852829933166504, "max": 1670.7860107421875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8518985645926516, "min": 1.7408103966154158, "max": 4.055232123878058, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2480.6226755976677, "min": 222.82373076677322, "max": 2606.091960608959, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8518985645926516, "min": 1.7408103966154158, "max": 4.055232123878058, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2480.6226755976677, "min": 222.82373076677322, "max": 2606.091960608959, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.015092481177837019, "min": 0.014680570008931684, "max": 0.01958322270559923, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.045277443533511055, "min": 0.029383830394363035, "max": 0.05641823809904357, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0679010309278965, "min": 0.022298337643345198, "max": 0.0679010309278965, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.20370309278368948, "min": 0.044596675286690396, "max": 0.20370309278368948, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7864987378666677e-06, "min": 3.7864987378666677e-06, "max": 0.00029535622654792493, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1359496213600003e-05, "min": 1.1359496213600003e-05, "max": 0.0008439288186903998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10126213333333338, "min": 0.10126213333333338, "max": 0.198452075, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037864000000001, "min": 0.20766530000000002, "max": 0.5813096000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.298045333333334e-05, "min": 7.298045333333334e-05, "max": 0.004922758542500001, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021894136000000003, "min": 0.00021894136000000003, "max": 0.01406734904, "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": "1671496178", "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": "1671498372" }, "total": 2193.872290874, "count": 1, "self": 0.39426421799998934, "children": { "run_training.setup": { "total": 0.10338428300002533, "count": 1, "self": 0.10338428300002533 }, "TrainerController.start_learning": { "total": 2193.374642373, "count": 1, "self": 3.9952749570202286, "children": { "TrainerController._reset_env": { "total": 7.255434564999973, "count": 1, "self": 7.255434564999973 }, "TrainerController.advance": { "total": 2182.0137219079793, "count": 233396, "self": 4.226200159867858, "children": { "env_step": { "total": 1716.1417872830223, "count": 233396, "self": 1441.207074096081, "children": { "SubprocessEnvManager._take_step": { "total": 272.28364946094223, "count": 233396, "self": 14.191178423967415, "children": { "TorchPolicy.evaluate": { "total": 258.0924710369748, "count": 222899, "self": 65.59129928696717, "children": { "TorchPolicy.sample_actions": { "total": 192.50117175000764, "count": 222899, "self": 192.50117175000764 } } } } }, "workers": { "total": 2.6510637259991086, "count": 233396, "self": 0.0, "children": { "worker_root": { "total": 2185.763029541078, "count": 233396, "is_parallel": true, "self": 1001.5112100180716, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.001958474000048227, "count": 1, "is_parallel": true, "self": 0.0003347590000544187, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016237149999938083, "count": 2, "is_parallel": true, "self": 0.0016237149999938083 } } }, "UnityEnvironment.step": { "total": 0.02687739100002773, "count": 1, "is_parallel": true, "self": 0.00027273800003513315, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00019119600000294668, "count": 1, "is_parallel": true, "self": 0.00019119600000294668 }, "communicator.exchange": { "total": 0.02573161500004062, "count": 1, "is_parallel": true, "self": 0.02573161500004062 }, "steps_from_proto": { "total": 0.0006818419999490288, "count": 1, "is_parallel": true, "self": 0.0002404389999810519, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044140299996797694, "count": 2, "is_parallel": true, "self": 0.00044140299996797694 } } } } } } }, "UnityEnvironment.step": { "total": 1184.2518195230066, "count": 233395, "is_parallel": true, "self": 34.54092763494623, "children": { "UnityEnvironment._generate_step_input": { "total": 74.45402156700516, "count": 233395, "is_parallel": true, "self": 74.45402156700516 }, "communicator.exchange": { "total": 982.3514171780567, "count": 233395, "is_parallel": true, "self": 982.3514171780567 }, "steps_from_proto": { "total": 92.90545314299834, "count": 233395, "is_parallel": true, "self": 37.54973771795886, "children": { "_process_rank_one_or_two_observation": { "total": 55.35571542503948, "count": 466790, "is_parallel": true, "self": 55.35571542503948 } } } } } } } } } } }, "trainer_advance": { "total": 461.6457344650891, "count": 233396, "self": 6.284691750130662, "children": { "process_trajectory": { "total": 148.84061258895844, "count": 233396, "self": 147.70731866395823, "children": { "RLTrainer._checkpoint": { "total": 1.1332939250002028, "count": 10, "self": 1.1332939250002028 } } }, "_update_policy": { "total": 306.520430126, "count": 97, "self": 254.02658740300336, "children": { "TorchPPOOptimizer.update": { "total": 52.493842722996646, "count": 2910, "self": 52.493842722996646 } } } } } } }, "trainer_threads": { "total": 8.920001164369751e-07, "count": 1, "self": 8.920001164369751e-07 }, "TrainerController._save_models": { "total": 0.11021005100019465, "count": 1, "self": 0.001853812000263133, "children": { "RLTrainer._checkpoint": { "total": 0.10835623899993152, "count": 1, "self": 0.10835623899993152 } } } } } } }