ppo-Huggy / run_logs /timers.json
svetaU's picture
My Huggy
07757b5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4084837436676025,
"min": 1.4084837436676025,
"max": 1.4272576570510864,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70927.015625,
"min": 69128.5234375,
"max": 75566.125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.3091537132988,
"min": 81.29111842105263,
"max": 396.90551181102364,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49394.0,
"min": 49200.0,
"max": 50407.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999990.0,
"min": 49784.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999990.0,
"min": 49784.0,
"max": 1999990.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3909366130828857,
"min": 0.09755469858646393,
"max": 2.451308250427246,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1384.352294921875,
"min": 12.291892051696777,
"max": 1458.31298828125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8090130502489976,
"min": 1.981396086395733,
"max": 3.9237310960256386,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2205.4185560941696,
"min": 249.65590688586235,
"max": 2332.09910517931,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8090130502489976,
"min": 1.981396086395733,
"max": 3.9237310960256386,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2205.4185560941696,
"min": 249.65590688586235,
"max": 2332.09910517931,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015594378343990278,
"min": 0.012192533494408053,
"max": 0.020259251758640556,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04678313503197083,
"min": 0.024385066988816106,
"max": 0.05935910034459084,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.052304679693447216,
"min": 0.022498395883788665,
"max": 0.056805701243380705,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15691403908034166,
"min": 0.04499679176757733,
"max": 0.17017827878395717,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.735548754850007e-06,
"min": 3.735548754850007e-06,
"max": 0.00029533215155594996,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.120664626455002e-05,
"min": 1.120664626455002e-05,
"max": 0.00084412606862465,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124515,
"min": 0.10124515,
"max": 0.19844405,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30373545,
"min": 0.20764214999999997,
"max": 0.5813753500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.213298500000012e-05,
"min": 7.213298500000012e-05,
"max": 0.004922358094999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021639895500000038,
"min": 0.00021639895500000038,
"max": 0.014070629964999998,
"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": "1726700150",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.4.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726705050"
},
"total": 4899.884997986001,
"count": 1,
"self": 1.0455055500005983,
"children": {
"run_training.setup": {
"total": 0.13257035800006634,
"count": 1,
"self": 0.13257035800006634
},
"TrainerController.start_learning": {
"total": 4898.7069220779995,
"count": 1,
"self": 8.686332363856309,
"children": {
"TrainerController._reset_env": {
"total": 3.9398329179998655,
"count": 1,
"self": 3.9398329179998655
},
"TrainerController.advance": {
"total": 4885.910145682143,
"count": 232169,
"self": 9.030891657360371,
"children": {
"env_step": {
"total": 3085.0999625870213,
"count": 232169,
"self": 2567.349274817768,
"children": {
"SubprocessEnvManager._take_step": {
"total": 512.0256793992266,
"count": 232169,
"self": 32.79613814218874,
"children": {
"TorchPolicy.evaluate": {
"total": 479.2295412570379,
"count": 222931,
"self": 479.2295412570379
}
}
},
"workers": {
"total": 5.725008370026444,
"count": 232169,
"self": 0.0,
"children": {
"worker_root": {
"total": 4885.180761104782,
"count": 232169,
"is_parallel": true,
"self": 2842.662453287776,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017277380002269638,
"count": 1,
"is_parallel": true,
"self": 0.00045615200042448123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012715859998024825,
"count": 2,
"is_parallel": true,
"self": 0.0012715859998024825
}
}
},
"UnityEnvironment.step": {
"total": 0.06713098000000173,
"count": 1,
"is_parallel": true,
"self": 0.0005274240002108854,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002757249999376654,
"count": 1,
"is_parallel": true,
"self": 0.0002757249999376654
},
"communicator.exchange": {
"total": 0.06536805799987633,
"count": 1,
"is_parallel": true,
"self": 0.06536805799987633
},
"steps_from_proto": {
"total": 0.000959772999976849,
"count": 1,
"is_parallel": true,
"self": 0.0002465180000399414,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007132549999369076,
"count": 2,
"is_parallel": true,
"self": 0.0007132549999369076
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 2042.5183078170057,
"count": 232168,
"is_parallel": true,
"self": 63.47962009661251,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 112.49242079286068,
"count": 232168,
"is_parallel": true,
"self": 112.49242079286068
},
"communicator.exchange": {
"total": 1729.7193324677164,
"count": 232168,
"is_parallel": true,
"self": 1729.7193324677164
},
"steps_from_proto": {
"total": 136.82693445981613,
"count": 232168,
"is_parallel": true,
"self": 44.129972368098606,
"children": {
"_process_rank_one_or_two_observation": {
"total": 92.69696209171752,
"count": 464336,
"is_parallel": true,
"self": 92.69696209171752
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1791.779291437761,
"count": 232169,
"self": 13.97005088888227,
"children": {
"process_trajectory": {
"total": 257.42441839787443,
"count": 232169,
"self": 256.1507014458771,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2737169519973577,
"count": 10,
"self": 1.2737169519973577
}
}
},
"_update_policy": {
"total": 1520.3848221510043,
"count": 97,
"self": 347.47341246602537,
"children": {
"TorchPPOOptimizer.update": {
"total": 1172.911409684979,
"count": 2910,
"self": 1172.911409684979
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.497000084782485e-06,
"count": 1,
"self": 1.497000084782485e-06
},
"TrainerController._save_models": {
"total": 0.17060961700008193,
"count": 1,
"self": 0.004090137999810395,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16651947900027153,
"count": 1,
"self": 0.16651947900027153
}
}
}
}
}
}
}