|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.2831450402736664, |
|
"min": 0.27647390961647034, |
|
"max": 1.3314456939697266, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 8458.1083984375, |
|
"min": 8263.251953125, |
|
"max": 40390.73828125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 989903.0, |
|
"min": 29952.0, |
|
"max": 989903.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 989903.0, |
|
"min": 29952.0, |
|
"max": 989903.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.5331242084503174, |
|
"min": -0.08161784708499908, |
|
"max": 0.6086713671684265, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 145.00978088378906, |
|
"min": -19.66990089416504, |
|
"max": 171.64532470703125, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.013147570192813873, |
|
"min": 0.008359591476619244, |
|
"max": 0.35875093936920166, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 3.576138973236084, |
|
"min": 2.232010841369629, |
|
"max": 86.10022735595703, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.07074687161920813, |
|
"min": 0.06528083108291947, |
|
"max": 0.07387718798893571, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9904562026689139, |
|
"min": 0.5171403159225499, |
|
"max": 1.0519662533884446, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.014774359902297701, |
|
"min": 0.0010657111923892332, |
|
"max": 0.016704808535790972, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.20684103863216782, |
|
"min": 0.0127885343086708, |
|
"max": 0.23386731950107362, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 7.44468323275714e-06, |
|
"min": 7.44468323275714e-06, |
|
"max": 0.00029515063018788575, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.00010422556525859996, |
|
"min": 0.00010422556525859996, |
|
"max": 0.0033299562900145994, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.10248152857142857, |
|
"min": 0.10248152857142857, |
|
"max": 0.19838354285714285, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4347414, |
|
"min": 1.3886848, |
|
"max": 2.4429815, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.00025790470428571426, |
|
"min": 0.00025790470428571426, |
|
"max": 0.00983851593142857, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.00361066586, |
|
"min": 0.00361066586, |
|
"max": 0.11100754146000003, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.011992672458291054, |
|
"min": 0.011992672458291054, |
|
"max": 0.44280704855918884, |
|
"count": 33 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.16789741814136505, |
|
"min": 0.16789741814136505, |
|
"max": 3.099649429321289, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 337.632183908046, |
|
"min": 323.7738095238095, |
|
"max": 999.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 29374.0, |
|
"min": 15984.0, |
|
"max": 33480.0, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.587590790685566, |
|
"min": -1.0000000521540642, |
|
"max": 1.6524095114852702, |
|
"count": 33 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 138.12039878964424, |
|
"min": -30.371001690626144, |
|
"max": 152.8417981788516, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.587590790685566, |
|
"min": -1.0000000521540642, |
|
"max": 1.6524095114852702, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 138.12039878964424, |
|
"min": -30.371001690626144, |
|
"max": 152.8417981788516, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.042656828530250525, |
|
"min": 0.04155728800817467, |
|
"max": 8.673599689267576, |
|
"count": 33 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 3.7111440821317956, |
|
"min": 3.6239896253391635, |
|
"max": 138.7775950282812, |
|
"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": "1682008481", |
|
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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", |
|
"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": "1682010667" |
|
}, |
|
"total": 2185.639243634, |
|
"count": 1, |
|
"self": 0.4746151539998209, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.18756779000023016, |
|
"count": 1, |
|
"self": 0.18756779000023016 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 2184.97706069, |
|
"count": 1, |
|
"self": 1.3177440959616433, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 4.206724615999974, |
|
"count": 1, |
|
"self": 4.206724615999974 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 2179.3499813390385, |
|
"count": 63986, |
|
"self": 1.4295142691371439, |
|
"children": { |
|
"env_step": { |
|
"total": 1577.1854947989464, |
|
"count": 63986, |
|
"self": 1471.737605235025, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 104.63379173691374, |
|
"count": 63986, |
|
"self": 4.7763616609377095, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 99.85743007597603, |
|
"count": 62562, |
|
"self": 99.85743007597603 |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.814097827007572, |
|
"count": 63986, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 2180.2727685519753, |
|
"count": 63986, |
|
"is_parallel": true, |
|
"self": 817.3340112089627, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0027553879999686615, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0008322000003317953, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0019231879996368662, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0019231879996368662 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.0514542790001542, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000545565000265924, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.000558977999844501, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.000558977999844501 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.048624609999933455, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.048624609999933455 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.001725126000110322, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00038822100123070413, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0013369049988796178, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0013369049988796178 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 1362.9387573430126, |
|
"count": 63985, |
|
"is_parallel": true, |
|
"self": 31.63894305388567, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 23.451805826031432, |
|
"count": 63985, |
|
"is_parallel": true, |
|
"self": 23.451805826031432 |
|
}, |
|
"communicator.exchange": { |
|
"total": 1212.560337047049, |
|
"count": 63985, |
|
"is_parallel": true, |
|
"self": 1212.560337047049 |
|
}, |
|
"steps_from_proto": { |
|
"total": 95.28767141604658, |
|
"count": 63985, |
|
"is_parallel": true, |
|
"self": 20.61780366001767, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 74.6698677560289, |
|
"count": 511880, |
|
"is_parallel": true, |
|
"self": 74.6698677560289 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 600.734972270955, |
|
"count": 63986, |
|
"self": 2.491997850956068, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 104.01509944899863, |
|
"count": 63986, |
|
"self": 103.81317694399877, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.20192250499985676, |
|
"count": 2, |
|
"self": 0.20192250499985676 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 494.22787497100035, |
|
"count": 448, |
|
"self": 314.92275043594555, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 179.3051245350548, |
|
"count": 22815, |
|
"self": 179.3051245350548 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 8.699998943484388e-07, |
|
"count": 1, |
|
"self": 8.699998943484388e-07 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.10260976900008245, |
|
"count": 1, |
|
"self": 0.001463841999793658, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.1011459270002888, |
|
"count": 1, |
|
"self": 0.1011459270002888 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |