ppo-PyramidsRND / run_logs /timers.json
Davide Paolini
First Commit
6a460a8
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.49634885787963867,
"min": 0.49634885787963867,
"max": 1.4964333772659302,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 14731.6337890625,
"min": 14731.6337890625,
"max": 45395.8046875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989950.0,
"min": 29952.0,
"max": 989950.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989950.0,
"min": 29952.0,
"max": 989950.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.46727025508880615,
"min": -0.10360406339168549,
"max": 0.5503093600273132,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 124.76115417480469,
"min": -24.864974975585938,
"max": 150.78475952148438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.0009803205030038953,
"min": -0.002041361527517438,
"max": 0.34527358412742615,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -0.2617455720901489,
"min": -0.5572916865348816,
"max": 82.86566162109375,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0664495444244833,
"min": 0.06478786239013597,
"max": 0.07215392828848231,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9302936219427662,
"min": 0.48232102043252306,
"max": 1.0662336423861858,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014605709413740378,
"min": 9.729337644818929e-05,
"max": 0.015433623640359762,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2044799317923653,
"min": 0.0012648138938264608,
"max": 0.21607073096503668,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.2211204700635713e-05,
"min": 1.2211204700635713e-05,
"max": 0.0004919177159021714,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001709568658089,
"min": 0.0001709568658089,
"max": 0.005373161625367697,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10244222142857144,
"min": 0.10244222142857144,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4341911000000003,
"min": 1.3691136000000002,
"max": 2.4016173000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002539779207142857,
"min": 0.0002539779207142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035556908899999997,
"min": 0.0035556908899999997,
"max": 0.10747576677000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010972365736961365,
"min": 0.010972365736961365,
"max": 0.4672490060329437,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1536131203174591,
"min": 0.1536131203174591,
"max": 3.2707431316375732,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 383.70666666666665,
"min": 346.7261904761905,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 28778.0,
"min": 15984.0,
"max": 33248.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.481031981309255,
"min": -1.0000000521540642,
"max": 1.6078216710004463,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 111.07739859819412,
"min": -32.000001668930054,
"max": 134.874197691679,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.481031981309255,
"min": -1.0000000521540642,
"max": 1.6078216710004463,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 111.07739859819412,
"min": -32.000001668930054,
"max": 134.874197691679,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.044745957035726557,
"min": 0.04135403070124864,
"max": 8.702322350814939,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.355946777679492,
"min": 3.355946777679492,
"max": 139.23715761303902,
"count": 33
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 33
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1683645706",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
"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": "1683647753"
},
"total": 2047.356567905,
"count": 1,
"self": 0.4387848850001319,
"children": {
"run_training.setup": {
"total": 0.04040912899995419,
"count": 1,
"self": 0.04040912899995419
},
"TrainerController.start_learning": {
"total": 2046.877373891,
"count": 1,
"self": 1.2476063740534755,
"children": {
"TrainerController._reset_env": {
"total": 4.073559272000011,
"count": 1,
"self": 4.073559272000011
},
"TrainerController.advance": {
"total": 2041.4604496149464,
"count": 63594,
"self": 1.3350876329086532,
"children": {
"env_step": {
"total": 1420.641720377004,
"count": 63594,
"self": 1313.2480586259953,
"children": {
"SubprocessEnvManager._take_step": {
"total": 106.62063830398517,
"count": 63594,
"self": 4.639438844959159,
"children": {
"TorchPolicy.evaluate": {
"total": 101.98119945902602,
"count": 62562,
"self": 101.98119945902602
}
}
},
"workers": {
"total": 0.7730234470234336,
"count": 63594,
"self": 0.0,
"children": {
"worker_root": {
"total": 2042.1708213150398,
"count": 63594,
"is_parallel": true,
"self": 839.0515123340713,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004787438999983351,
"count": 1,
"is_parallel": true,
"self": 0.003635471000166035,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001151967999817316,
"count": 8,
"is_parallel": true,
"self": 0.001151967999817316
}
}
},
"UnityEnvironment.step": {
"total": 0.04912798299994847,
"count": 1,
"is_parallel": true,
"self": 0.0005457259999275266,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043430300002000877,
"count": 1,
"is_parallel": true,
"self": 0.00043430300002000877
},
"communicator.exchange": {
"total": 0.046579044999930375,
"count": 1,
"is_parallel": true,
"self": 0.046579044999930375
},
"steps_from_proto": {
"total": 0.0015689090000705619,
"count": 1,
"is_parallel": true,
"self": 0.0003331369999841627,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012357720000863992,
"count": 8,
"is_parallel": true,
"self": 0.0012357720000863992
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1203.1193089809685,
"count": 63593,
"is_parallel": true,
"self": 31.294097765996412,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 21.88594282995234,
"count": 63593,
"is_parallel": true,
"self": 21.88594282995234
},
"communicator.exchange": {
"total": 1055.488022943976,
"count": 63593,
"is_parallel": true,
"self": 1055.488022943976
},
"steps_from_proto": {
"total": 94.45124544104374,
"count": 63593,
"is_parallel": true,
"self": 19.121798938074676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.32944650296906,
"count": 508744,
"is_parallel": true,
"self": 75.32944650296906
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 619.4836416050337,
"count": 63594,
"self": 2.4372668739752044,
"children": {
"process_trajectory": {
"total": 103.19894631906163,
"count": 63594,
"self": 102.88783307506151,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31111324400012563,
"count": 2,
"self": 0.31111324400012563
}
}
},
"_update_policy": {
"total": 513.8474284119968,
"count": 438,
"self": 329.40305000603166,
"children": {
"TorchPPOOptimizer.update": {
"total": 184.44437840596515,
"count": 22803,
"self": 184.44437840596515
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0710000424296595e-06,
"count": 1,
"self": 1.0710000424296595e-06
},
"TrainerController._save_models": {
"total": 0.09575755900004879,
"count": 1,
"self": 0.0014274980003392557,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09433006099970953,
"count": 1,
"self": 0.09433006099970953
}
}
}
}
}
}
}