testpyramidsrnd / run_logs /timers.json
kws's picture
First Pyramids
5ea6aca
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3722575902938843,
"min": 0.36756157875061035,
"max": 1.4197617769241333,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11126.03515625,
"min": 11015.0849609375,
"max": 43069.89453125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989940.0,
"min": 29952.0,
"max": 989940.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4362761676311493,
"min": -0.09901584684848785,
"max": 0.4362761676311493,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 118.23084259033203,
"min": -23.86281967163086,
"max": 118.23084259033203,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -2.320399284362793,
"min": -2.320399284362793,
"max": 0.5477666854858398,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -628.8281860351562,
"min": -628.8281860351562,
"max": 129.82070922851562,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06680335942468298,
"min": 0.0634971892549878,
"max": 0.07284381275526124,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9352470319455616,
"min": 0.5091302945432802,
"max": 1.0484980045002885,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.5465176464074764,
"min": 6.57791112738937e-05,
"max": 0.5465176464074764,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 7.6512470497046685,
"min": 0.0009209075578345119,
"max": 7.6512470497046685,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.4121975293e-06,
"min": 7.4121975293e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001037707654102,
"min": 0.0001037707654102,
"max": 0.0035068061310647,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10247070000000004,
"min": 0.10247070000000004,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4345898000000006,
"min": 1.3691136000000002,
"max": 2.5689353,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00025682293000000005,
"min": 0.00025682293000000005,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0035955210200000007,
"min": 0.0035955210200000007,
"max": 0.11691663646999997,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010524674318730831,
"min": 0.010499625466763973,
"max": 0.6446754336357117,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1473454385995865,
"min": 0.14699475467205048,
"max": 4.512728214263916,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 391.30263157894734,
"min": 391.30263157894734,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29739.0,
"min": 15984.0,
"max": 32152.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5297368257061432,
"min": -1.0000000521540642,
"max": 1.5297368257061432,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 116.25999875366688,
"min": -32.000001668930054,
"max": 116.25999875366688,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5297368257061432,
"min": -1.0000000521540642,
"max": 1.5297368257061432,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 116.25999875366688,
"min": -32.000001668930054,
"max": 116.25999875366688,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04391795104004957,
"min": 0.04391795104004957,
"max": 13.879449147731066,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.3377642790437676,
"min": 3.146501191826246,
"max": 222.07118636369705,
"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": "1661157625",
"python_version": "3.7.13 (default, Apr 24 2022, 01:04:09) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1661159708"
},
"total": 2082.187716556,
"count": 1,
"self": 0.43390301699946576,
"children": {
"run_training.setup": {
"total": 0.04172459400001571,
"count": 1,
"self": 0.04172459400001571
},
"TrainerController.start_learning": {
"total": 2081.7120889450002,
"count": 1,
"self": 1.396067616005439,
"children": {
"TrainerController._reset_env": {
"total": 9.303450071999919,
"count": 1,
"self": 9.303450071999919
},
"TrainerController.advance": {
"total": 2070.9045348799946,
"count": 63455,
"self": 1.4418085730144412,
"children": {
"env_step": {
"total": 1357.2290385590445,
"count": 63455,
"self": 1247.1763313000993,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.3159531089326,
"count": 63455,
"self": 4.654667319922055,
"children": {
"TorchPolicy.evaluate": {
"total": 104.66128578901055,
"count": 62570,
"self": 35.72163834102582,
"children": {
"TorchPolicy.sample_actions": {
"total": 68.93964744798473,
"count": 62570,
"self": 68.93964744798473
}
}
}
}
},
"workers": {
"total": 0.7367541500127572,
"count": 63455,
"self": 0.0,
"children": {
"worker_root": {
"total": 2077.6625517810344,
"count": 63455,
"is_parallel": true,
"self": 934.487049008007,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005237267999973483,
"count": 1,
"is_parallel": true,
"self": 0.004041340000071614,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001195927999901869,
"count": 8,
"is_parallel": true,
"self": 0.001195927999901869
}
}
},
"UnityEnvironment.step": {
"total": 0.04657564199999342,
"count": 1,
"is_parallel": true,
"self": 0.0005281489999333644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000565635000043585,
"count": 1,
"is_parallel": true,
"self": 0.000565635000043585
},
"communicator.exchange": {
"total": 0.04386161800005084,
"count": 1,
"is_parallel": true,
"self": 0.04386161800005084
},
"steps_from_proto": {
"total": 0.0016202399999656336,
"count": 1,
"is_parallel": true,
"self": 0.00040618699983951956,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001214053000126114,
"count": 8,
"is_parallel": true,
"self": 0.001214053000126114
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1143.1755027730273,
"count": 63454,
"is_parallel": true,
"self": 27.60050904099444,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.041987192990746,
"count": 63454,
"is_parallel": true,
"self": 24.041987192990746
},
"communicator.exchange": {
"total": 996.4305986990142,
"count": 63454,
"is_parallel": true,
"self": 996.4305986990142
},
"steps_from_proto": {
"total": 95.10240784002792,
"count": 63454,
"is_parallel": true,
"self": 23.186578939167475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 71.91582890086045,
"count": 507632,
"is_parallel": true,
"self": 71.91582890086045
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 712.2336877479356,
"count": 63455,
"self": 2.5261689069478734,
"children": {
"process_trajectory": {
"total": 166.51548182899228,
"count": 63455,
"self": 166.31482473599226,
"children": {
"RLTrainer._checkpoint": {
"total": 0.200657093000018,
"count": 2,
"self": 0.200657093000018
}
}
},
"_update_policy": {
"total": 543.1920370119955,
"count": 444,
"self": 211.2822025099631,
"children": {
"TorchPPOOptimizer.update": {
"total": 331.90983450203237,
"count": 22836,
"self": 331.90983450203237
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2479999895731453e-06,
"count": 1,
"self": 1.2479999895731453e-06
},
"TrainerController._save_models": {
"total": 0.10803512900019996,
"count": 1,
"self": 0.0016176690005522687,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10641745999964769,
"count": 1,
"self": 0.10641745999964769
}
}
}
}
}
}
}