ppo-Huggy / run_logs /timers.json
mgmeskill's picture
Huggy
5791cf8
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3941048383712769,
"min": 1.3941048383712769,
"max": 1.4246137142181396,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70409.265625,
"min": 67593.296875,
"max": 76804.4375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.41333333333333,
"min": 82.74539363484087,
"max": 409.327868852459,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50092.0,
"min": 48940.0,
"max": 50125.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999913.0,
"min": 49896.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999913.0,
"min": 49896.0,
"max": 1999913.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4254770278930664,
"min": 0.01032092235982418,
"max": 2.465161085128784,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1273.37548828125,
"min": 1.2488316297531128,
"max": 1438.3779296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7159655075981504,
"min": 1.8993430984906914,
"max": 3.9410399659952398,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1950.881891489029,
"min": 229.82051491737366,
"max": 2248.1842056512833,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7159655075981504,
"min": 1.8993430984906914,
"max": 3.9410399659952398,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1950.881891489029,
"min": 229.82051491737366,
"max": 2248.1842056512833,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01459193047129601,
"min": 0.014042970005862623,
"max": 0.019962574700184633,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04377579141388803,
"min": 0.02843307679455999,
"max": 0.057172746264162314,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.049646280002262864,
"min": 0.020693938713520765,
"max": 0.05962972694800959,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1489388400067886,
"min": 0.04138787742704153,
"max": 0.17888918084402877,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.432648855816657e-06,
"min": 3.432648855816657e-06,
"max": 0.00029532135155955,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0297946567449971e-05,
"min": 1.0297946567449971e-05,
"max": 0.0008438635687121499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10171627500000002,
"min": 0.10171627500000002,
"max": 0.24766067500000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30514882500000007,
"min": 0.21115685000000006,
"max": 0.7219317749999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.709474833333319e-05,
"min": 6.709474833333319e-05,
"max": 0.004922178454999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020128424499999957,
"min": 0.00020128424499999957,
"max": 0.014066263714999997,
"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": "1686252122",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [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 --resume",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1686254792"
},
"total": 2669.942559883,
"count": 1,
"self": 0.42396789099984744,
"children": {
"run_training.setup": {
"total": 0.04676740700006121,
"count": 1,
"self": 0.04676740700006121
},
"TrainerController.start_learning": {
"total": 2669.471824585,
"count": 1,
"self": 5.019408485040003,
"children": {
"TrainerController._reset_env": {
"total": 3.9492492439999296,
"count": 1,
"self": 3.9492492439999296
},
"TrainerController.advance": {
"total": 2660.3822560859603,
"count": 232161,
"self": 5.253249258791584,
"children": {
"env_step": {
"total": 2085.1762853391742,
"count": 232161,
"self": 1756.0267485958952,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.0093284623358,
"count": 232161,
"self": 18.979222354366357,
"children": {
"TorchPolicy.evaluate": {
"total": 307.03010610796946,
"count": 222999,
"self": 307.03010610796946
}
}
},
"workers": {
"total": 3.1402082809431704,
"count": 232161,
"self": 0.0,
"children": {
"worker_root": {
"total": 2661.0162904720432,
"count": 232161,
"is_parallel": true,
"self": 1231.7747263486608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008528030002707965,
"count": 1,
"is_parallel": true,
"self": 0.00026783000021168846,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000584973000059108,
"count": 2,
"is_parallel": true,
"self": 0.000584973000059108
}
}
},
"UnityEnvironment.step": {
"total": 0.032277097000132926,
"count": 1,
"is_parallel": true,
"self": 0.0003349060002619808,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025712499973451486,
"count": 1,
"is_parallel": true,
"self": 0.00025712499973451486
},
"communicator.exchange": {
"total": 0.030869202999838308,
"count": 1,
"is_parallel": true,
"self": 0.030869202999838308
},
"steps_from_proto": {
"total": 0.0008158630002981226,
"count": 1,
"is_parallel": true,
"self": 0.0002520370003367134,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005638259999614093,
"count": 2,
"is_parallel": true,
"self": 0.0005638259999614093
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1429.2415641233824,
"count": 232160,
"is_parallel": true,
"self": 39.66000646022985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.55374593421129,
"count": 232160,
"is_parallel": true,
"self": 87.55374593421129
},
"communicator.exchange": {
"total": 1201.890508489033,
"count": 232160,
"is_parallel": true,
"self": 1201.890508489033
},
"steps_from_proto": {
"total": 100.1373032399083,
"count": 232160,
"is_parallel": true,
"self": 38.8894472586112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.24785598129711,
"count": 464320,
"is_parallel": true,
"self": 61.24785598129711
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 569.9527214879945,
"count": 232161,
"self": 7.457502394996936,
"children": {
"process_trajectory": {
"total": 152.18197969299717,
"count": 232161,
"self": 150.82694164299755,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3550380499996209,
"count": 10,
"self": 1.3550380499996209
}
}
},
"_update_policy": {
"total": 410.3132394000004,
"count": 97,
"self": 348.2267312250042,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.0865081749962,
"count": 2910,
"self": 62.0865081749962
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.369996405439451e-07,
"count": 1,
"self": 9.369996405439451e-07
},
"TrainerController._save_models": {
"total": 0.12090983300004154,
"count": 1,
"self": 0.0024793279999357765,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11843050500010577,
"count": 1,
"self": 0.11843050500010577
}
}
}
}
}
}
}