ppo-PyramidsRND / run_logs /timers.json
pruvost's picture
First Push
fbcdf58
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6155093312263489,
"min": 0.5640690922737122,
"max": 1.3926230669021606,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 18465.279296875,
"min": 16858.896484375,
"max": 42246.61328125,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989951.0,
"min": 29952.0,
"max": 989951.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989951.0,
"min": 29952.0,
"max": 989951.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3263048231601715,
"min": -0.1467040628194809,
"max": 0.3263048231601715,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 85.16555786132812,
"min": -35.20897674560547,
"max": 85.16555786132812,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.16536669433116913,
"min": -0.06129518151283264,
"max": 0.3146844506263733,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 43.16070556640625,
"min": -15.568976402282715,
"max": 74.58021545410156,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06905587064198535,
"min": 0.0646983808896324,
"max": 0.07378951320397495,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9667821889877949,
"min": 0.4896869255768754,
"max": 1.0864035822545275,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016141147909308085,
"min": 0.0004929111855085158,
"max": 0.016141147909308085,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22597607073031317,
"min": 0.004402704059769861,
"max": 0.22597607073031317,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.70864028762857e-06,
"min": 7.70864028762857e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010792096402679998,
"min": 0.00010792096402679998,
"max": 0.0032593055135649,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256951428571429,
"min": 0.10256951428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359732,
"min": 1.3691136000000002,
"max": 2.4018288,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002666944771428572,
"min": 0.0002666944771428572,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003733722680000001,
"min": 0.003733722680000001,
"max": 0.10866486649,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.013549591414630413,
"min": 0.013549591414630413,
"max": 0.45953649282455444,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18969428539276123,
"min": 0.18969428539276123,
"max": 3.2167553901672363,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 506.1475409836066,
"min": 506.1475409836066,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30875.0,
"min": 15984.0,
"max": 33314.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.1330950510550717,
"min": -1.0000000521540642,
"max": 1.1669018507566091,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 69.11879811435938,
"min": -32.000001668930054,
"max": 69.11879811435938,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.1330950510550717,
"min": -1.0000000521540642,
"max": 1.1669018507566091,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 69.11879811435938,
"min": -32.000001668930054,
"max": 69.11879811435938,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.07240822937933071,
"min": 0.07240822937933071,
"max": 9.206113990396261,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.416901992139174,
"min": 4.299042085032852,
"max": 147.29782384634018,
"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": "1675423945",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.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": "1675427171"
},
"total": 3225.854696502,
"count": 1,
"self": 0.5810654430001705,
"children": {
"run_training.setup": {
"total": 0.14612133500008895,
"count": 1,
"self": 0.14612133500008895
},
"TrainerController.start_learning": {
"total": 3225.1275097239995,
"count": 1,
"self": 2.4686468340291867,
"children": {
"TrainerController._reset_env": {
"total": 5.407122659999914,
"count": 1,
"self": 5.407122659999914
},
"TrainerController.advance": {
"total": 3217.1329879109703,
"count": 63384,
"self": 2.4435229049290683,
"children": {
"env_step": {
"total": 2050.611858534974,
"count": 63384,
"self": 1908.0878115069186,
"children": {
"SubprocessEnvManager._take_step": {
"total": 140.98922722700104,
"count": 63384,
"self": 6.675567312990779,
"children": {
"TorchPolicy.evaluate": {
"total": 134.31365991401026,
"count": 62560,
"self": 29.792481549983677,
"children": {
"TorchPolicy.sample_actions": {
"total": 104.52117836402658,
"count": 62560,
"self": 104.52117836402658
}
}
}
}
},
"workers": {
"total": 1.534819801054482,
"count": 63384,
"self": 0.0,
"children": {
"worker_root": {
"total": 3218.573048178947,
"count": 63384,
"is_parallel": true,
"self": 1477.3483497680438,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.003304783999965366,
"count": 1,
"is_parallel": true,
"self": 0.001256362999583871,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002048421000381495,
"count": 8,
"is_parallel": true,
"self": 0.002048421000381495
}
}
},
"UnityEnvironment.step": {
"total": 0.0883754520000366,
"count": 1,
"is_parallel": true,
"self": 0.0007133019998946111,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005771769999682874,
"count": 1,
"is_parallel": true,
"self": 0.0005771769999682874
},
"communicator.exchange": {
"total": 0.08138546200007113,
"count": 1,
"is_parallel": true,
"self": 0.08138546200007113
},
"steps_from_proto": {
"total": 0.005699511000102575,
"count": 1,
"is_parallel": true,
"self": 0.000746635000268725,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00495287599983385,
"count": 8,
"is_parallel": true,
"self": 0.00495287599983385
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1741.224698410903,
"count": 63383,
"is_parallel": true,
"self": 42.52028825494244,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 25.142879307939666,
"count": 63383,
"is_parallel": true,
"self": 25.142879307939666
},
"communicator.exchange": {
"total": 1534.8614576320415,
"count": 63383,
"is_parallel": true,
"self": 1534.8614576320415
},
"steps_from_proto": {
"total": 138.7000732159795,
"count": 63383,
"is_parallel": true,
"self": 32.540105706876375,
"children": {
"_process_rank_one_or_two_observation": {
"total": 106.15996750910313,
"count": 507064,
"is_parallel": true,
"self": 106.15996750910313
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1164.077606471067,
"count": 63384,
"self": 4.80535012318137,
"children": {
"process_trajectory": {
"total": 207.560465135884,
"count": 63384,
"self": 207.1983695838835,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3620955520004827,
"count": 2,
"self": 0.3620955520004827
}
}
},
"_update_policy": {
"total": 951.7117912120016,
"count": 439,
"self": 233.73468931997218,
"children": {
"TorchPPOOptimizer.update": {
"total": 717.9771018920294,
"count": 22839,
"self": 717.9771018920294
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.6290005078190006e-06,
"count": 1,
"self": 1.6290005078190006e-06
},
"TrainerController._save_models": {
"total": 0.11875068999961513,
"count": 1,
"self": 0.003657735999695433,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1150929539999197,
"count": 1,
"self": 0.1150929539999197
}
}
}
}
}
}
}