ppo-Huggy / run_logs /timers.json
ShounenJump's picture
Huggy
9c07c85 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4072821140289307,
"min": 1.4072760343551636,
"max": 1.4273849725723267,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71871.3046875,
"min": 66523.828125,
"max": 79341.2109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.19318181818181,
"min": 89.06557377049181,
"max": 376.85074626865674,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49206.0,
"min": 48848.0,
"max": 50498.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999930.0,
"min": 49938.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999930.0,
"min": 49938.0,
"max": 1999930.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.372891426086426,
"min": -0.04034437611699104,
"max": 2.4175033569335938,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1252.88671875,
"min": -5.365801811218262,
"max": 1309.937744140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6766941496594385,
"min": 1.7651315775132717,
"max": 3.883932004144147,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1941.2945110201836,
"min": 234.76249980926514,
"max": 2023.5379797816277,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6766941496594385,
"min": 1.7651315775132717,
"max": 3.883932004144147,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1941.2945110201836,
"min": 234.76249980926514,
"max": 2023.5379797816277,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01862465312102965,
"min": 0.014106866837796083,
"max": 0.020144216048841673,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05587395936308895,
"min": 0.028569275437136336,
"max": 0.05587395936308895,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05414345148536894,
"min": 0.023879405111074448,
"max": 0.06071875039488077,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16243035445610682,
"min": 0.047758810222148895,
"max": 0.16892238544921082,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.198248933949999e-06,
"min": 3.198248933949999e-06,
"max": 0.00029533447655517495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.594746801849998e-06,
"min": 9.594746801849998e-06,
"max": 0.00084374956875015,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106604999999998,
"min": 0.10106604999999998,
"max": 0.19844482499999994,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30319814999999994,
"min": 0.20726325,
"max": 0.58124985,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.3195895e-05,
"min": 6.3195895e-05,
"max": 0.004922396767500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018958768499999999,
"min": 0.00018958768499999999,
"max": 0.014064367514999999,
"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": "1743570698",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743573634"
},
"total": 2936.212802848,
"count": 1,
"self": 0.49042877500050963,
"children": {
"run_training.setup": {
"total": 0.035542032999956064,
"count": 1,
"self": 0.035542032999956064
},
"TrainerController.start_learning": {
"total": 2935.68683204,
"count": 1,
"self": 5.7772537810797076,
"children": {
"TrainerController._reset_env": {
"total": 3.2605499409999084,
"count": 1,
"self": 3.2605499409999084
},
"TrainerController.advance": {
"total": 2926.5094580529203,
"count": 231890,
"self": 5.582391492730494,
"children": {
"env_step": {
"total": 2376.949073925162,
"count": 231890,
"self": 1862.2853738730555,
"children": {
"SubprocessEnvManager._take_step": {
"total": 511.0961576029788,
"count": 231890,
"self": 18.85268502101667,
"children": {
"TorchPolicy.evaluate": {
"total": 492.2434725819621,
"count": 223040,
"self": 492.2434725819621
}
}
},
"workers": {
"total": 3.5675424491275862,
"count": 231890,
"self": 0.0,
"children": {
"worker_root": {
"total": 2926.8423074938896,
"count": 231890,
"is_parallel": true,
"self": 1414.8915007078142,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010792900000069494,
"count": 1,
"is_parallel": true,
"self": 0.00028363299975353584,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007956570002534136,
"count": 2,
"is_parallel": true,
"self": 0.0007956570002534136
}
}
},
"UnityEnvironment.step": {
"total": 0.033940199999960896,
"count": 1,
"is_parallel": true,
"self": 0.00033532700012983696,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023747199998069846,
"count": 1,
"is_parallel": true,
"self": 0.00023747199998069846
},
"communicator.exchange": {
"total": 0.032599572999970405,
"count": 1,
"is_parallel": true,
"self": 0.032599572999970405
},
"steps_from_proto": {
"total": 0.0007678279998799553,
"count": 1,
"is_parallel": true,
"self": 0.0002291079997576162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005387200001223391,
"count": 2,
"is_parallel": true,
"self": 0.0005387200001223391
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1511.9508067860754,
"count": 231889,
"is_parallel": true,
"self": 43.57045380488762,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 96.38043967120211,
"count": 231889,
"is_parallel": true,
"self": 96.38043967120211
},
"communicator.exchange": {
"total": 1267.7659189830244,
"count": 231889,
"is_parallel": true,
"self": 1267.7659189830244
},
"steps_from_proto": {
"total": 104.23399432696124,
"count": 231889,
"is_parallel": true,
"self": 38.84912292197487,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.38487140498637,
"count": 463778,
"is_parallel": true,
"self": 65.38487140498637
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 543.9779926350279,
"count": 231890,
"self": 8.595823264232877,
"children": {
"process_trajectory": {
"total": 186.97922977179724,
"count": 231890,
"self": 185.58703799179784,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3921917799993935,
"count": 10,
"self": 1.3921917799993935
}
}
},
"_update_policy": {
"total": 348.4029395989978,
"count": 97,
"self": 277.60910798399664,
"children": {
"TorchPPOOptimizer.update": {
"total": 70.79383161500118,
"count": 2910,
"self": 70.79383161500118
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1709998943842947e-06,
"count": 1,
"self": 1.1709998943842947e-06
},
"TrainerController._save_models": {
"total": 0.13956909399985307,
"count": 1,
"self": 0.0023659219996261527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13720317200022691,
"count": 1,
"self": 0.13720317200022691
}
}
}
}
}
}
}