ppo-Huggy / run_logs /timers.json
akilina's picture
Huggy
75de029 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.0338597297668457,
"min": 1.0338597297668457,
"max": 1.5451802015304565,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 51580.296875,
"min": 51331.859375,
"max": 78756.0078125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 140.82072829131653,
"min": 138.97752808988764,
"max": 383.1297709923664,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 50273.0,
"min": 49102.0,
"max": 50309.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999927.0,
"min": 49775.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999927.0,
"min": 49775.0,
"max": 1999927.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.9458972215652466,
"min": 0.13383056223392487,
"max": 2.0057482719421387,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 694.685302734375,
"min": 17.397974014282227,
"max": 700.18359375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.566481092730824,
"min": 1.7916743657909906,
"max": 3.7654838828103885,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1273.2337501049042,
"min": 232.9176675528288,
"max": 1295.58827739954,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.566481092730824,
"min": 1.7916743657909906,
"max": 3.7654838828103885,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1273.2337501049042,
"min": 232.9176675528288,
"max": 1295.58827739954,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018536103859514694,
"min": 0.01678921321472444,
"max": 0.052222587061745186,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03707220771902939,
"min": 0.03357842642944888,
"max": 0.15666776118523557,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.017096067022066563,
"min": 0.01198761307168752,
"max": 0.5671223873272537,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.03419213404413313,
"min": 0.024416705453768374,
"max": 1.1342447746545075,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 7.050634858987506e-05,
"min": 7.050634858987506e-05,
"max": 0.00492270750154585,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0001410126971797501,
"min": 0.0001410126971797501,
"max": 0.014064400018712002,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.101410125,
"min": 0.101410125,
"max": 0.19845415,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20282025,
"min": 0.20282025,
"max": 0.581288,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.036523750000005e-05,
"min": 8.036523750000005e-05,
"max": 0.004922862085,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001607304750000001,
"min": 0.0001607304750000001,
"max": 0.014066271200000001,
"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": "1740222777",
"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=Huggy --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": "1740225227"
},
"total": 2450.8707485679997,
"count": 1,
"self": 0.43604575599965756,
"children": {
"run_training.setup": {
"total": 0.022875746999943658,
"count": 1,
"self": 0.022875746999943658
},
"TrainerController.start_learning": {
"total": 2450.411827065,
"count": 1,
"self": 4.315452898999865,
"children": {
"TrainerController._reset_env": {
"total": 3.2477822190001007,
"count": 1,
"self": 3.2477822190001007
},
"TrainerController.advance": {
"total": 2442.731860432,
"count": 228118,
"self": 4.762044097869875,
"children": {
"env_step": {
"total": 1907.7101848000927,
"count": 228118,
"self": 1480.4359872599962,
"children": {
"SubprocessEnvManager._take_step": {
"total": 424.7514668931485,
"count": 228118,
"self": 15.346301178149588,
"children": {
"TorchPolicy.evaluate": {
"total": 409.40516571499893,
"count": 222706,
"self": 409.40516571499893
}
}
},
"workers": {
"total": 2.522730646948048,
"count": 228118,
"self": 0.0,
"children": {
"worker_root": {
"total": 2443.472520465067,
"count": 228118,
"is_parallel": true,
"self": 1237.8462711161599,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009908449999329605,
"count": 1,
"is_parallel": true,
"self": 0.00021258199967633118,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007782630002566293,
"count": 2,
"is_parallel": true,
"self": 0.0007782630002566293
}
}
},
"UnityEnvironment.step": {
"total": 0.029467372999988584,
"count": 1,
"is_parallel": true,
"self": 0.0003208299999641895,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002042500000243308,
"count": 1,
"is_parallel": true,
"self": 0.0002042500000243308
},
"communicator.exchange": {
"total": 0.02825081500009219,
"count": 1,
"is_parallel": true,
"self": 0.02825081500009219
},
"steps_from_proto": {
"total": 0.0006914779999078746,
"count": 1,
"is_parallel": true,
"self": 0.00018773500005409005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005037429998537846,
"count": 2,
"is_parallel": true,
"self": 0.0005037429998537846
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1205.6262493489073,
"count": 228117,
"is_parallel": true,
"self": 36.423809588827226,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 78.57255252400705,
"count": 228117,
"is_parallel": true,
"self": 78.57255252400705
},
"communicator.exchange": {
"total": 1006.7308573190664,
"count": 228117,
"is_parallel": true,
"self": 1006.7308573190664
},
"steps_from_proto": {
"total": 83.8990299170066,
"count": 228117,
"is_parallel": true,
"self": 29.17303055905677,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.72599935794983,
"count": 456234,
"is_parallel": true,
"self": 54.72599935794983
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 530.259631534037,
"count": 228118,
"self": 6.595514951113728,
"children": {
"process_trajectory": {
"total": 131.57512213192513,
"count": 228118,
"self": 130.78291253892417,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7922095930009618,
"count": 6,
"self": 0.7922095930009618
}
}
},
"_update_policy": {
"total": 392.08899445099814,
"count": 96,
"self": 308.4979537549932,
"children": {
"TorchPPOOptimizer.update": {
"total": 83.59104069600494,
"count": 3840,
"self": 83.59104069600494
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.530000741302501e-07,
"count": 1,
"self": 8.530000741302501e-07
},
"TrainerController._save_models": {
"total": 0.11673066200000903,
"count": 1,
"self": 0.001857110999935685,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11487355100007335,
"count": 1,
"self": 0.11487355100007335
}
}
}
}
}
}
}