ppo-Huggy / run_logs /timers.json
Boxnixta's picture
Huggy
2e2ebe3 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4050616025924683,
"min": 1.4050616025924683,
"max": 1.4280853271484375,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69542.1171875,
"min": 68647.7890625,
"max": 75467.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 94.78202676864245,
"min": 85.23168654173764,
"max": 373.7851851851852,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49571.0,
"min": 48793.0,
"max": 50461.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999991.0,
"min": 49982.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999991.0,
"min": 49982.0,
"max": 1999991.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3639776706695557,
"min": 0.2761019170284271,
"max": 2.4374988079071045,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1236.3603515625,
"min": 36.997657775878906,
"max": 1387.46044921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.64383964123735,
"min": 1.8442617234454226,
"max": 4.009033547200072,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1905.728132367134,
"min": 247.13107094168663,
"max": 2197.063748061657,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.64383964123735,
"min": 1.8442617234454226,
"max": 4.009033547200072,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1905.728132367134,
"min": 247.13107094168663,
"max": 2197.063748061657,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017066895176882705,
"min": 0.014068597706500442,
"max": 0.02209383327863179,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03413379035376541,
"min": 0.029769295259029604,
"max": 0.06231193918914262,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04811739722887675,
"min": 0.020873956661671397,
"max": 0.05849473097672065,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0962347944577535,
"min": 0.041747913323342795,
"max": 0.158357605834802,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.580048473350005e-06,
"min": 4.580048473350005e-06,
"max": 0.0002953224765591749,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.16009694670001e-06,
"min": 9.16009694670001e-06,
"max": 0.0008439564186811998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10152665000000002,
"min": 0.10152665000000002,
"max": 0.19844082499999993,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20305330000000005,
"min": 0.20305330000000005,
"max": 0.5813188,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.617983500000008e-05,
"min": 8.617983500000008e-05,
"max": 0.004922197167500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00017235967000000016,
"min": 0.00017235967000000016,
"max": 0.01406780812,
"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": "1781870437",
"python_version": "3.10.11 (main, May 16 2023, 00:28:57) [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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1781873111"
},
"total": 2674.216820987,
"count": 1,
"self": 0.4511440980008956,
"children": {
"run_training.setup": {
"total": 0.02545497599976443,
"count": 1,
"self": 0.02545497599976443
},
"TrainerController.start_learning": {
"total": 2673.7402219129995,
"count": 1,
"self": 4.474499842009209,
"children": {
"TrainerController._reset_env": {
"total": 2.8822395920001327,
"count": 1,
"self": 2.8822395920001327
},
"TrainerController.advance": {
"total": 2666.28532760899,
"count": 232169,
"self": 5.063249083171286,
"children": {
"env_step": {
"total": 2191.851024804887,
"count": 232169,
"self": 1749.218039512873,
"children": {
"SubprocessEnvManager._take_step": {
"total": 439.78153508197056,
"count": 232169,
"self": 16.163775548903686,
"children": {
"TorchPolicy.evaluate": {
"total": 423.6177595330669,
"count": 222990,
"self": 423.6177595330669
}
}
},
"workers": {
"total": 2.8514502100433674,
"count": 232169,
"self": 0.0,
"children": {
"worker_root": {
"total": 2661.302980395846,
"count": 232169,
"is_parallel": true,
"self": 1250.9814787948098,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009910650001074828,
"count": 1,
"is_parallel": true,
"self": 0.000281006000477646,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007100589996298368,
"count": 2,
"is_parallel": true,
"self": 0.0007100589996298368
}
}
},
"UnityEnvironment.step": {
"total": 0.0350596560001577,
"count": 1,
"is_parallel": true,
"self": 0.0003304610004306596,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001955759998963913,
"count": 1,
"is_parallel": true,
"self": 0.0001955759998963913
},
"communicator.exchange": {
"total": 0.033724072000040906,
"count": 1,
"is_parallel": true,
"self": 0.033724072000040906
},
"steps_from_proto": {
"total": 0.0008095469997897453,
"count": 1,
"is_parallel": true,
"self": 0.00019623099979071412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006133159999990312,
"count": 2,
"is_parallel": true,
"self": 0.0006133159999990312
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1410.3215016010363,
"count": 232168,
"is_parallel": true,
"self": 39.22084504123268,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.26606767970179,
"count": 232168,
"is_parallel": true,
"self": 85.26606767970179
},
"communicator.exchange": {
"total": 1192.6771165949854,
"count": 232168,
"is_parallel": true,
"self": 1192.6771165949854
},
"steps_from_proto": {
"total": 93.15747228511646,
"count": 232168,
"is_parallel": true,
"self": 33.71488913882558,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.44258314629087,
"count": 464336,
"is_parallel": true,
"self": 59.44258314629087
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 469.37105372093174,
"count": 232169,
"self": 6.794374892867836,
"children": {
"process_trajectory": {
"total": 160.31930718807098,
"count": 232169,
"self": 159.1072700790728,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2120371089981745,
"count": 10,
"self": 1.2120371089981745
}
}
},
"_update_policy": {
"total": 302.2573716399929,
"count": 96,
"self": 238.8484690209998,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.408902618993125,
"count": 2880,
"self": 63.408902618993125
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.020004654303193e-07,
"count": 1,
"self": 9.020004654303193e-07
},
"TrainerController._save_models": {
"total": 0.09815396799967857,
"count": 1,
"self": 0.001223852999828523,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09693011499985005,
"count": 1,
"self": 0.09693011499985005
}
}
}
}
}
}
}