{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4038903713226318, "min": 1.4038903713226318, "max": 1.427829623222351, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70062.5546875, "min": 68507.96875, "max": 76696.28125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 82.98991596638655, "min": 81.30642504118616, "max": 389.16279069767444, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49379.0, "min": 48857.0, "max": 50202.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999929.0, "min": 49790.0, "max": 1999929.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999929.0, "min": 49790.0, "max": 1999929.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.412655830383301, "min": 0.14084318280220032, "max": 2.5014915466308594, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1435.5302734375, "min": 18.02792739868164, "max": 1483.20361328125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7765000269192606, "min": 1.8718320714542642, "max": 4.0427348513769195, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2247.01751601696, "min": 239.59450514614582, "max": 2309.7410638332367, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7765000269192606, "min": 1.8718320714542642, "max": 4.0427348513769195, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2247.01751601696, "min": 239.59450514614582, "max": 2309.7410638332367, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.018442926885715374, "min": 0.013078648783751607, "max": 0.019931669790013175, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.05532878065714612, "min": 0.026157297567503214, "max": 0.05979500937003952, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.0583064306113455, "min": 0.02175634019076824, "max": 0.05923438469568888, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1749192918340365, "min": 0.04351268038153648, "max": 0.1755847370872895, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.536448821216666e-06, "min": 3.536448821216666e-06, "max": 0.000295327276557575, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0609346463649999e-05, "min": 1.0609346463649999e-05, "max": 0.0008441922186025998, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117878333333334, "min": 0.10117878333333334, "max": 0.19844242500000003, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30353635, "min": 0.20750925000000003, "max": 0.5813974000000001, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.882128833333333e-05, "min": 6.882128833333333e-05, "max": 0.0049222770075000016, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.000206463865, "min": 0.000206463865, "max": 0.01407173026, "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": "1677218628", "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]", "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": "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": "1.22.4", "end_time_seconds": "1677221088" }, "total": 2460.140035291, "count": 1, "self": 0.6063721410000653, "children": { "run_training.setup": { "total": 0.11631609100004425, "count": 1, "self": 0.11631609100004425 }, "TrainerController.start_learning": { "total": 2459.417347059, "count": 1, "self": 4.416409466959067, "children": { "TrainerController._reset_env": { "total": 11.23388047800006, "count": 1, "self": 11.23388047800006 }, "TrainerController.advance": { "total": 2443.6607116420405, "count": 232562, "self": 4.8706897719644076, "children": { "env_step": { "total": 1906.8323288250872, "count": 232562, "self": 1593.8138935092802, "children": { "SubprocessEnvManager._take_step": { "total": 310.15843744093024, "count": 232562, "self": 16.504553200036867, "children": { "TorchPolicy.evaluate": { "total": 293.6538842408934, "count": 222840, "self": 73.11258341600853, "children": { "TorchPolicy.sample_actions": { "total": 220.54130082488484, "count": 222840, "self": 220.54130082488484 } } } } }, "workers": { "total": 2.859997874876626, "count": 232562, "self": 0.0, "children": { "worker_root": { "total": 2450.505328999139, "count": 232562, "is_parallel": true, "self": 1157.45835102016, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0009462780000148996, "count": 1, "is_parallel": true, "self": 0.00039488300001266907, "children": { "_process_rank_one_or_two_observation": { "total": 0.0005513950000022305, "count": 2, "is_parallel": true, "self": 0.0005513950000022305 } } }, "UnityEnvironment.step": { "total": 0.03227747400001135, "count": 1, "is_parallel": true, "self": 0.0002998250000700864, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00020521299995834852, "count": 1, "is_parallel": true, "self": 0.00020521299995834852 }, "communicator.exchange": { "total": 0.028838398999937453, "count": 1, "is_parallel": true, "self": 0.028838398999937453 }, "steps_from_proto": { "total": 0.002934037000045464, "count": 1, "is_parallel": true, "self": 0.00028913000005559297, "children": { "_process_rank_one_or_two_observation": { "total": 0.002644906999989871, "count": 2, "is_parallel": true, "self": 0.002644906999989871 } } } } } } }, "UnityEnvironment.step": { "total": 1293.0469779789787, "count": 232561, "is_parallel": true, "self": 38.29145148100315, "children": { "UnityEnvironment._generate_step_input": { "total": 82.57368308501111, "count": 232561, "is_parallel": true, "self": 82.57368308501111 }, "communicator.exchange": { "total": 1078.3687772709104, "count": 232561, "is_parallel": true, "self": 1078.3687772709104 }, "steps_from_proto": { "total": 93.81306614205403, "count": 232561, "is_parallel": true, "self": 40.39339385625942, "children": { "_process_rank_one_or_two_observation": { "total": 53.419672285794604, "count": 465122, "is_parallel": true, "self": 53.419672285794604 } } } } } } } } } } }, "trainer_advance": { "total": 531.957693044989, "count": 232562, "self": 6.974680235989126, "children": { "process_trajectory": { "total": 171.59470032200056, "count": 232562, "self": 170.3857388869999, "children": { "RLTrainer._checkpoint": { "total": 1.208961435000674, "count": 10, "self": 1.208961435000674 } } }, "_update_policy": { "total": 353.3883124869993, "count": 97, "self": 295.5859977150029, "children": { "TorchPPOOptimizer.update": { "total": 57.80231477199641, "count": 2910, "self": 57.80231477199641 } } } } } } }, "trainer_threads": { "total": 9.37000095291296e-07, "count": 1, "self": 9.37000095291296e-07 }, "TrainerController._save_models": { "total": 0.10634453500006202, "count": 1, "self": 0.0019216720002077636, "children": { "RLTrainer._checkpoint": { "total": 0.10442286299985426, "count": 1, "self": 0.10442286299985426 } } } } } } }