ppo-pyramids / run_logs /timers.json
sinny's picture
First Push
5be28a4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 1.34518563747406,
"min": 1.34518563747406,
"max": 1.6037851572036743,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 37751.2890625,
"min": 32165.931640625,
"max": 77443.578125,
"count": 10
},
"Pyramids.Step.mean": {
"value": 299967.0,
"min": 29952.0,
"max": 299967.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 299967.0,
"min": 29952.0,
"max": 299967.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.05793962627649307,
"min": -0.10416014492511749,
"max": 0.23007497191429138,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -13.731691360473633,
"min": -26.560836791992188,
"max": 53.83754348754883,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.03692026808857918,
"min": 0.03692026808857918,
"max": 0.4226361811161041,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 8.750103950500488,
"min": 8.750103950500488,
"max": 98.89686584472656,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07005543610178874,
"min": 0.0679856052720394,
"max": 0.07626096354492586,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.7005543610178874,
"min": 0.4188352679581537,
"max": 0.7005543610178874,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0019222434540856943,
"min": 0.00010227638162835699,
"max": 0.008823805660119467,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.019222434540856943,
"min": 0.0009204874346552129,
"max": 0.0529428339607168,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5821194726300002e-05,
"min": 1.5821194726300002e-05,
"max": 0.00028429867190044446,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00015821194726300003,
"min": 0.00015821194726300003,
"max": 0.0017866561044479997,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1052737,
"min": 0.1052737,
"max": 0.1947662222222222,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.052737,
"min": 0.9207493333333333,
"max": 1.5492856666666668,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005368426300000002,
"min": 0.0005368426300000002,
"max": 0.009477145600000002,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.005368426300000002,
"min": 0.005368426300000002,
"max": 0.05956564480000001,
"count": 10
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.03076792322099209,
"min": 0.03076792322099209,
"max": 0.5195443630218506,
"count": 10
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.3076792359352112,
"min": 0.267240047454834,
"max": 3.1172661781311035,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 719.8,
"min": 224.0,
"max": 999.0,
"count": 7
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 3599.0,
"min": 224.0,
"max": 109890.0,
"count": 7
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.47991997599601743,
"min": -1.0000000521540642,
"max": 1.7760000377893448,
"count": 7
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 2.3995998799800873,
"min": -114.00000594556332,
"max": 4.744999885559082,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.47991997599601743,
"min": -1.0000000521540642,
"max": 1.7760000377893448,
"count": 7
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 2.3995998799800873,
"min": -114.00000594556332,
"max": 4.744999885559082,
"count": 7
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.311483626998961,
"min": 0.13982895761728287,
"max": 2.633639372885227,
"count": 7
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.5574181349948049,
"min": 0.13982895761728287,
"max": 185.76088354550302,
"count": 7
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1688722554",
"python_version": "3.9.13 (main, Oct 13 2022, 21:15:33) \n[GCC 11.2.0]",
"command_line_arguments": "/home/olav/dev/anaconda3/envs/hug-rl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=pyramids_training_and_5 --no-graphics --force",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1",
"numpy_version": "1.21.2",
"end_time_seconds": "1688722716"
},
"total": 161.608135203016,
"count": 1,
"self": 0.3211399420397356,
"children": {
"run_training.setup": {
"total": 0.031840882962569594,
"count": 1,
"self": 0.031840882962569594
},
"TrainerController.start_learning": {
"total": 161.25515437801369,
"count": 1,
"self": 0.2723246969981119,
"children": {
"TrainerController._reset_env": {
"total": 1.5905830189585686,
"count": 1,
"self": 1.5905830189585686
},
"TrainerController.advance": {
"total": 159.29549783305265,
"count": 14022,
"self": 0.22901960194576532,
"children": {
"env_step": {
"total": 67.68740833661286,
"count": 14022,
"self": 40.967237195174675,
"children": {
"SubprocessEnvManager._take_step": {
"total": 26.5403018881334,
"count": 19549,
"self": 0.9354832168319263,
"children": {
"TorchPolicy.evaluate": {
"total": 25.604818671301473,
"count": 19537,
"self": 25.604818671301473
}
}
},
"workers": {
"total": 0.17986925330478698,
"count": 14022,
"self": 0.0,
"children": {
"worker_root": {
"total": 1931.958879199694,
"count": 19538,
"is_parallel": true,
"self": 1218.0949142348836,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.011932429915759712,
"count": 12,
"is_parallel": true,
"self": 0.003587272483855486,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008345157431904227,
"count": 96,
"is_parallel": true,
"self": 0.008345157431904227
}
}
},
"UnityEnvironment.step": {
"total": 0.7438849699101411,
"count": 12,
"is_parallel": true,
"self": 0.001948183518834412,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.008791721193119884,
"count": 12,
"is_parallel": true,
"self": 0.008791721193119884
},
"communicator.exchange": {
"total": 0.7219343140604906,
"count": 12,
"is_parallel": true,
"self": 0.7219343140604906
},
"steps_from_proto": {
"total": 0.011210751137696207,
"count": 12,
"is_parallel": true,
"self": 0.002771151135675609,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.008439600002020597,
"count": 96,
"is_parallel": true,
"self": 0.008439600002020597
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 713.8639649648103,
"count": 19526,
"is_parallel": true,
"self": 3.0717344526201487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.246067003114149,
"count": 19526,
"is_parallel": true,
"self": 13.246067003114149
},
"communicator.exchange": {
"total": 680.3323255372234,
"count": 19526,
"is_parallel": true,
"self": 680.3323255372234
},
"steps_from_proto": {
"total": 17.213837971852627,
"count": 19526,
"is_parallel": true,
"self": 4.171758057316765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.042079914535861,
"count": 156208,
"is_parallel": true,
"self": 13.042079914535861
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 91.37906989449402,
"count": 14022,
"self": 0.3428757885703817,
"children": {
"process_trajectory": {
"total": 17.308251061011106,
"count": 14022,
"self": 17.308251061011106
},
"_update_policy": {
"total": 73.72794304491254,
"count": 82,
"self": 45.66784885386005,
"children": {
"TorchPPOOptimizer.update": {
"total": 28.060094191052485,
"count": 6978,
"self": 28.060094191052485
}
}
}
}
}
}
},
"trainer_threads": {
"total": 6.899936124682426e-07,
"count": 1,
"self": 6.899936124682426e-07
},
"TrainerController._save_models": {
"total": 0.0967481390107423,
"count": 1,
"self": 0.029211898043286055,
"children": {
"RLTrainer._checkpoint": {
"total": 0.06753624096745625,
"count": 1,
"self": 0.06753624096745625
}
}
}
}
}
}
}