ppo-Huggy / run_logs /timers.json
dkimds's picture
Huggy
7ca8ed0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4004302024841309,
"min": 1.4004302024841309,
"max": 1.4262583255767822,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68081.9140625,
"min": 68081.9140625,
"max": 78196.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 97.96435643564357,
"min": 95.43713733075435,
"max": 429.2307692307692,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49472.0,
"min": 48882.0,
"max": 50252.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999979.0,
"min": 49637.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999979.0,
"min": 49637.0,
"max": 1999979.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2594141960144043,
"min": 0.14686760306358337,
"max": 2.3832757472991943,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1141.004150390625,
"min": 17.03664207458496,
"max": 1199.7755126953125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.516566003077101,
"min": 1.7345707326613624,
"max": 3.822230178105513,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1775.865831553936,
"min": 201.21020498871803,
"max": 1878.4543128609657,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.516566003077101,
"min": 1.7345707326613624,
"max": 3.822230178105513,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1775.865831553936,
"min": 201.21020498871803,
"max": 1878.4543128609657,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01719263567647431,
"min": 0.01395681169560703,
"max": 0.021491428615991025,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05157790702942293,
"min": 0.02791362339121406,
"max": 0.06074451818518961,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0559815557466613,
"min": 0.020615710007647673,
"max": 0.0559815557466613,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16794466723998389,
"min": 0.041231420015295346,
"max": 0.16794466723998389,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4852488382833376e-06,
"min": 3.4852488382833376e-06,
"max": 0.00029537160154279995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0455746514850013e-05,
"min": 1.0455746514850013e-05,
"max": 0.0008442708185764,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10116171666666668,
"min": 0.10116171666666668,
"max": 0.1984572,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30348515000000004,
"min": 0.20745315000000003,
"max": 0.5814236,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.796966166666676e-05,
"min": 6.796966166666676e-05,
"max": 0.00492301428,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020390898500000025,
"min": 0.00020390898500000025,
"max": 0.014073037640000001,
"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": "1691128411",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "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": "1691130800"
},
"total": 2388.881204716,
"count": 1,
"self": 0.4448188580004171,
"children": {
"run_training.setup": {
"total": 0.04259190699985993,
"count": 1,
"self": 0.04259190699985993
},
"TrainerController.start_learning": {
"total": 2388.3937939509997,
"count": 1,
"self": 4.306985507846093,
"children": {
"TrainerController._reset_env": {
"total": 5.354955404000066,
"count": 1,
"self": 5.354955404000066
},
"TrainerController.advance": {
"total": 2378.6116954151535,
"count": 230937,
"self": 4.460870527301267,
"children": {
"env_step": {
"total": 1837.9771468219517,
"count": 230937,
"self": 1546.3793509958577,
"children": {
"SubprocessEnvManager._take_step": {
"total": 288.72114723113214,
"count": 230937,
"self": 16.452813238160616,
"children": {
"TorchPolicy.evaluate": {
"total": 272.2683339929715,
"count": 222812,
"self": 272.2683339929715
}
}
},
"workers": {
"total": 2.8766485949618072,
"count": 230937,
"self": 0.0,
"children": {
"worker_root": {
"total": 2380.7118798068636,
"count": 230937,
"is_parallel": true,
"self": 1118.883198856881,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008316810001360864,
"count": 1,
"is_parallel": true,
"self": 0.00023375000023406756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005979309999020188,
"count": 2,
"is_parallel": true,
"self": 0.0005979309999020188
}
}
},
"UnityEnvironment.step": {
"total": 0.028821818999858806,
"count": 1,
"is_parallel": true,
"self": 0.0003249149999646761,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023634800004401768,
"count": 1,
"is_parallel": true,
"self": 0.00023634800004401768
},
"communicator.exchange": {
"total": 0.027522293999936664,
"count": 1,
"is_parallel": true,
"self": 0.027522293999936664
},
"steps_from_proto": {
"total": 0.0007382619999134477,
"count": 1,
"is_parallel": true,
"self": 0.00021456500007843715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005236969998350105,
"count": 2,
"is_parallel": true,
"self": 0.0005236969998350105
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1261.8286809499825,
"count": 230936,
"is_parallel": true,
"self": 39.9901386570491,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.67841827503844,
"count": 230936,
"is_parallel": true,
"self": 80.67841827503844
},
"communicator.exchange": {
"total": 1044.2920749139435,
"count": 230936,
"is_parallel": true,
"self": 1044.2920749139435
},
"steps_from_proto": {
"total": 96.86804910395153,
"count": 230936,
"is_parallel": true,
"self": 34.32889549385186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.539153610099675,
"count": 461872,
"is_parallel": true,
"self": 62.539153610099675
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 536.1736780659005,
"count": 230937,
"self": 6.617444577875631,
"children": {
"process_trajectory": {
"total": 128.63122919402372,
"count": 230937,
"self": 127.35226315702448,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2789660369992362,
"count": 10,
"self": 1.2789660369992362
}
}
},
"_update_policy": {
"total": 400.92500429400116,
"count": 97,
"self": 341.01757321800915,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.90743107599201,
"count": 2910,
"self": 59.90743107599201
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1819997780548874e-06,
"count": 1,
"self": 1.1819997780548874e-06
},
"TrainerController._save_models": {
"total": 0.12015644200027964,
"count": 1,
"self": 0.0018938820003313594,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11826255999994828,
"count": 1,
"self": 0.11826255999994828
}
}
}
}
}
}
}