ppo-Huggy / run_logs /timers.json
buming's picture
Huggy
1c70863 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407366394996643,
"min": 1.407366394996643,
"max": 1.427056908607483,
"count": 27
},
"Huggy.Policy.Entropy.sum": {
"value": 70980.5234375,
"min": 69033.609375,
"max": 76027.0,
"count": 27
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.13946587537092,
"min": 73.13946587537092,
"max": 388.0232558139535,
"count": 27
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49296.0,
"min": 48819.0,
"max": 50055.0,
"count": 27
},
"Huggy.Step.mean": {
"value": 1349963.0,
"min": 49645.0,
"max": 1349963.0,
"count": 27
},
"Huggy.Step.sum": {
"value": 1349963.0,
"min": 49645.0,
"max": 1349963.0,
"count": 27
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.484285593032837,
"min": 0.0020764051005244255,
"max": 2.512502670288086,
"count": 27
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1674.408447265625,
"min": 0.26577985286712646,
"max": 1674.408447265625,
"count": 27
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.877990810913573,
"min": 1.8546640407294035,
"max": 4.03156340662265,
"count": 27
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2613.765806555748,
"min": 237.39699721336365,
"max": 2635.131586909294,
"count": 27
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.877990810913573,
"min": 1.8546640407294035,
"max": 4.03156340662265,
"count": 27
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2613.765806555748,
"min": 237.39699721336365,
"max": 2635.131586909294,
"count": 27
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01707222784170881,
"min": 0.013366104699283217,
"max": 0.01978468738719433,
"count": 27
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03414445568341762,
"min": 0.026732209398566433,
"max": 0.059354062161582996,
"count": 27
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05860996227711439,
"min": 0.02399419510944022,
"max": 0.06315953539063533,
"count": 27
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11721992455422878,
"min": 0.04836170294632514,
"max": 0.17861839371422927,
"count": 27
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00010114596628469998,
"min": 0.00010114596628469998,
"max": 0.00029533747655417504,
"count": 27
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00020229193256939996,
"min": 0.00020229193256939996,
"max": 0.0008443393685535498,
"count": 27
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.13371530000000004,
"min": 0.13371530000000004,
"max": 0.19844582499999996,
"count": 27
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2674306000000001,
"min": 0.2674306000000001,
"max": 0.5814464500000002,
"count": 27
},
"Huggy.Policy.Beta.mean": {
"value": 0.0016923934700000002,
"min": 0.0016923934700000002,
"max": 0.004922446667500002,
"count": 27
},
"Huggy.Policy.Beta.sum": {
"value": 0.0033847869400000005,
"min": 0.0033847869400000005,
"max": 0.014074177855000002,
"count": 27
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 27
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 27
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1716308078",
"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=Huggy2 --no-graphics --force",
"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": "1716309841"
},
"total": 1763.261998556,
"count": 1,
"self": 0.40170531999979175,
"children": {
"run_training.setup": {
"total": 0.04954138700009025,
"count": 1,
"self": 0.04954138700009025
},
"TrainerController.start_learning": {
"total": 1762.810751849,
"count": 1,
"self": 3.305026209028483,
"children": {
"TrainerController._reset_env": {
"total": 1.9476358989998062,
"count": 1,
"self": 1.9476358989998062
},
"TrainerController.advance": {
"total": 1757.2085189049717,
"count": 161606,
"self": 3.447980998896128,
"children": {
"env_step": {
"total": 1396.4047740360538,
"count": 161606,
"self": 1155.4685889820664,
"children": {
"SubprocessEnvManager._take_step": {
"total": 238.81745752996744,
"count": 161606,
"self": 11.679653766952924,
"children": {
"TorchPolicy.evaluate": {
"total": 227.13780376301452,
"count": 155034,
"self": 227.13780376301452
}
}
},
"workers": {
"total": 2.1187275240199597,
"count": 161605,
"self": 0.0,
"children": {
"worker_root": {
"total": 1757.5574083128938,
"count": 161605,
"is_parallel": true,
"self": 825.6881077198377,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008920880000005127,
"count": 1,
"is_parallel": true,
"self": 0.00023615500003870693,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006559329999618058,
"count": 2,
"is_parallel": true,
"self": 0.0006559329999618058
}
}
},
"UnityEnvironment.step": {
"total": 0.03297669499988842,
"count": 1,
"is_parallel": true,
"self": 0.00041173299996444257,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002274309999847901,
"count": 1,
"is_parallel": true,
"self": 0.0002274309999847901
},
"communicator.exchange": {
"total": 0.03146012000001974,
"count": 1,
"is_parallel": true,
"self": 0.03146012000001974
},
"steps_from_proto": {
"total": 0.0008774109999194479,
"count": 1,
"is_parallel": true,
"self": 0.00025506400015729014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006223469997621578,
"count": 2,
"is_parallel": true,
"self": 0.0006223469997621578
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 931.8693005930561,
"count": 161604,
"is_parallel": true,
"self": 27.95357038522866,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 59.42316824995305,
"count": 161604,
"is_parallel": true,
"self": 59.42316824995305
},
"communicator.exchange": {
"total": 778.3627937449758,
"count": 161604,
"is_parallel": true,
"self": 778.3627937449758
},
"steps_from_proto": {
"total": 66.12976821289863,
"count": 161604,
"is_parallel": true,
"self": 24.939436146868957,
"children": {
"_process_rank_one_or_two_observation": {
"total": 41.19033206602967,
"count": 323208,
"is_parallel": true,
"self": 41.19033206602967
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 357.35576387002175,
"count": 161605,
"self": 4.66662606113573,
"children": {
"process_trajectory": {
"total": 115.2647748948882,
"count": 161605,
"self": 114.48523282588849,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7795420689997172,
"count": 6,
"self": 0.7795420689997172
}
}
},
"_update_policy": {
"total": 237.4243629139978,
"count": 67,
"self": 192.45326675599767,
"children": {
"TorchPPOOptimizer.update": {
"total": 44.97109615800014,
"count": 2010,
"self": 44.97109615800014
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.725999936752487e-06,
"count": 1,
"self": 1.725999936752487e-06
},
"TrainerController._save_models": {
"total": 0.349569110000175,
"count": 1,
"self": 0.0041291230004389945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.345439986999736,
"count": 1,
"self": 0.345439986999736
}
}
}
}
}
}
}