ppo-PyramidsRND / run_logs /timers.json
joen2010's picture
First Push
3cd3080 verified
raw
history blame
18.8 kB
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.14446556568145752,
"min": 0.14446556568145752,
"max": 1.444345235824585,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4329.34423828125,
"min": 4329.34423828125,
"max": 43815.65625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999995.0,
"min": 29952.0,
"max": 2999995.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999995.0,
"min": 29952.0,
"max": 2999995.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7704235315322876,
"min": -0.10181490331888199,
"max": 0.8655116558074951,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 228.8157958984375,
"min": -24.537391662597656,
"max": 263.11553955078125,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.016733018681406975,
"min": 0.0011387375416234136,
"max": 0.555656373500824,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.9697065353393555,
"min": 0.3108753561973572,
"max": 131.69056701660156,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06988161647585038,
"min": 0.06204224426050851,
"max": 0.07483950753770285,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9783426306619054,
"min": 0.4822765194875156,
"max": 1.0786946713342331,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01392988887444629,
"min": 0.00039698107112373356,
"max": 0.02598050595420415,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19501844424224804,
"min": 0.00555773499573227,
"max": 0.26956557048833935,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5683637629595244e-06,
"min": 1.5683637629595244e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1957092681433342e-05,
"min": 2.1957092681433342e-05,
"max": 0.0039275268908244,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10052275476190477,
"min": 0.10052275476190477,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4073185666666668,
"min": 1.3897045333333333,
"max": 2.7973922,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.222320071428574e-05,
"min": 6.222320071428574e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008711248100000005,
"min": 0.0008711248100000005,
"max": 0.13092664244000002,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008425016887485981,
"min": 0.008099747821688652,
"max": 0.6463526487350464,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.11795023083686829,
"min": 0.11600933969020844,
"max": 4.524468421936035,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 222.0597014925373,
"min": 207.645390070922,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29756.0,
"min": 15984.0,
"max": 32511.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.761954872175715,
"min": -1.0000000521540642,
"max": 1.7871785570468222,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 234.3399979993701,
"min": -32.000001668930054,
"max": 251.8519984483719,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.761954872175715,
"min": -1.0000000521540642,
"max": 1.7871785570468222,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 234.3399979993701,
"min": -32.000001668930054,
"max": 251.8519984483719,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.019676849928105082,
"min": 0.017501125833372988,
"max": 15.005290312692523,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.617021040437976,
"min": 2.4676587425055914,
"max": 240.08464500308037,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1712438014",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/home/joeny/.local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1712441530"
},
"total": 3516.1791991659993,
"count": 1,
"self": 0.2688839359998383,
"children": {
"run_training.setup": {
"total": 0.03330624399950466,
"count": 1,
"self": 0.03330624399950466
},
"TrainerController.start_learning": {
"total": 3515.877008986,
"count": 1,
"self": 3.147021408013643,
"children": {
"TrainerController._reset_env": {
"total": 1.5705331240005762,
"count": 1,
"self": 1.5705331240005762
},
"TrainerController.advance": {
"total": 3511.0439016629844,
"count": 194833,
"self": 3.0325700815346863,
"children": {
"env_step": {
"total": 2382.5480493187533,
"count": 194833,
"self": 2118.9429423037627,
"children": {
"SubprocessEnvManager._take_step": {
"total": 261.4096492479948,
"count": 194833,
"self": 8.231087012253738,
"children": {
"TorchPolicy.evaluate": {
"total": 253.17856223574108,
"count": 187554,
"self": 253.17856223574108
}
}
},
"workers": {
"total": 2.195457766995787,
"count": 194833,
"self": 0.0,
"children": {
"worker_root": {
"total": 3511.8801136623697,
"count": 194833,
"is_parallel": true,
"self": 1610.1382468191578,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0011475289993541082,
"count": 1,
"is_parallel": true,
"self": 0.000341423000463692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008061059988904162,
"count": 8,
"is_parallel": true,
"self": 0.0008061059988904162
}
}
},
"UnityEnvironment.step": {
"total": 0.0254131720002988,
"count": 1,
"is_parallel": true,
"self": 0.0005840149988216581,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019179200080543524,
"count": 1,
"is_parallel": true,
"self": 0.00019179200080543524
},
"communicator.exchange": {
"total": 0.023148442000092473,
"count": 1,
"is_parallel": true,
"self": 0.023148442000092473
},
"steps_from_proto": {
"total": 0.0014889230005792342,
"count": 1,
"is_parallel": true,
"self": 0.0002428700017844676,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012460529987947666,
"count": 8,
"is_parallel": true,
"self": 0.0012460529987947666
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1901.741866843212,
"count": 194832,
"is_parallel": true,
"self": 61.07512853609114,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 32.398689086351624,
"count": 194832,
"is_parallel": true,
"self": 32.398689086351624
},
"communicator.exchange": {
"total": 1653.8236376497634,
"count": 194832,
"is_parallel": true,
"self": 1653.8236376497634
},
"steps_from_proto": {
"total": 154.44441157100573,
"count": 194832,
"is_parallel": true,
"self": 31.70061374753186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 122.74379782347387,
"count": 1558656,
"is_parallel": true,
"self": 122.74379782347387
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1125.4632822626963,
"count": 194833,
"self": 5.892573370757418,
"children": {
"process_trajectory": {
"total": 220.0148202569244,
"count": 194833,
"self": 219.5871394479209,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4276808090035047,
"count": 6,
"self": 0.4276808090035047
}
}
},
"_update_policy": {
"total": 899.5558886350145,
"count": 1392,
"self": 520.4894827230446,
"children": {
"TorchPPOOptimizer.update": {
"total": 379.0664059119699,
"count": 68403,
"self": 379.0664059119699
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.830006557516754e-07,
"count": 1,
"self": 5.830006557516754e-07
},
"TrainerController._save_models": {
"total": 0.11555220800073585,
"count": 1,
"self": 0.0009456030020373873,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11460660499869846,
"count": 1,
"self": 0.11460660499869846
}
}
}
}
}
}
}