ppo-Pyramid / run_logs /timers.json
articblue's picture
Initial
dc53d0f
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5194954872131348,
"min": 0.5194954872131348,
"max": 1.4462867975234985,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 15493.43359375,
"min": 15493.43359375,
"max": 43874.5546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989968.0,
"min": 29952.0,
"max": 989968.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.1458946168422699,
"min": -0.1106647402048111,
"max": 0.24622873961925507,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 36.76544189453125,
"min": -26.670202255249023,
"max": 62.54209899902344,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.026137476786971092,
"min": 0.002795648528262973,
"max": 0.4412865936756134,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.586644172668457,
"min": 0.7045034170150757,
"max": 104.58492279052734,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06893026576076142,
"min": 0.06256623480094634,
"max": 0.07361850349904667,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9650237206506599,
"min": 0.5089311360952915,
"max": 1.074549947399646,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.00803071586495421,
"min": 0.00080885337797436,
"max": 0.01055655007370487,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.11243002210935894,
"min": 0.01051509391366668,
"max": 0.14779170103186817,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.51334035272857e-06,
"min": 7.51334035272857e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010518676493819997,
"min": 0.00010518676493819997,
"max": 0.0033737785754071993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10250441428571429,
"min": 0.10250441428571429,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4350618,
"min": 1.3691136000000002,
"max": 2.4423466,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026019098714285714,
"min": 0.00026019098714285714,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00364267382,
"min": 0.00364267382,
"max": 0.11247682072000004,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01313088834285736,
"min": 0.01313088834285736,
"max": 0.4959159195423126,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.18383243680000305,
"min": 0.18383243680000305,
"max": 3.4714114665985107,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 684.75,
"min": 568.9607843137255,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30129.0,
"min": 15984.0,
"max": 32378.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 0.7241090537810867,
"min": -1.0000000521540642,
"max": 1.0457249558530748,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 31.860798366367817,
"min": -32.000001668930054,
"max": 50.19479788094759,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 0.7241090537810867,
"min": -1.0000000521540642,
"max": 1.0457249558530748,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 31.860798366367817,
"min": -32.000001668930054,
"max": 50.19479788094759,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.09189357375461524,
"min": 0.08353373939341206,
"max": 9.831176722422242,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.04331724520307,
"min": 4.009619490883779,
"max": 157.29882755875587,
"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": "1704661141",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.21.2",
"end_time_seconds": "1704663306"
},
"total": 2164.643684074,
"count": 1,
"self": 0.47573000299962587,
"children": {
"run_training.setup": {
"total": 0.04430502400009573,
"count": 1,
"self": 0.04430502400009573
},
"TrainerController.start_learning": {
"total": 2164.123649047,
"count": 1,
"self": 1.2947348631723798,
"children": {
"TrainerController._reset_env": {
"total": 2.0669722620004904,
"count": 1,
"self": 2.0669722620004904
},
"TrainerController.advance": {
"total": 2160.678765534827,
"count": 63368,
"self": 1.3628125847471892,
"children": {
"env_step": {
"total": 1483.1958540350233,
"count": 63368,
"self": 1356.0193679740214,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.36956710710274,
"count": 63368,
"self": 4.700433714939209,
"children": {
"TorchPolicy.evaluate": {
"total": 121.66913339216353,
"count": 62570,
"self": 121.66913339216353
}
}
},
"workers": {
"total": 0.806918953899185,
"count": 63368,
"self": 0.0,
"children": {
"worker_root": {
"total": 2159.4685585579073,
"count": 63368,
"is_parallel": true,
"self": 916.9583185640759,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025024299993674504,
"count": 1,
"is_parallel": true,
"self": 0.0006718350014125463,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001830594997954904,
"count": 8,
"is_parallel": true,
"self": 0.001830594997954904
}
}
},
"UnityEnvironment.step": {
"total": 0.05393392199948721,
"count": 1,
"is_parallel": true,
"self": 0.0006532399984280346,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047769899992999854,
"count": 1,
"is_parallel": true,
"self": 0.00047769899992999854
},
"communicator.exchange": {
"total": 0.05083203600042907,
"count": 1,
"is_parallel": true,
"self": 0.05083203600042907
},
"steps_from_proto": {
"total": 0.0019709470007001073,
"count": 1,
"is_parallel": true,
"self": 0.0004065490011271322,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001564397999572975,
"count": 8,
"is_parallel": true,
"self": 0.001564397999572975
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1242.5102399938314,
"count": 63367,
"is_parallel": true,
"self": 34.34950486664093,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.452452414151594,
"count": 63367,
"is_parallel": true,
"self": 23.452452414151594
},
"communicator.exchange": {
"total": 1077.7102839969712,
"count": 63367,
"is_parallel": true,
"self": 1077.7102839969712
},
"steps_from_proto": {
"total": 106.99799871606774,
"count": 63367,
"is_parallel": true,
"self": 20.633007132775674,
"children": {
"_process_rank_one_or_two_observation": {
"total": 86.36499158329207,
"count": 506936,
"is_parallel": true,
"self": 86.36499158329207
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 676.1200989150566,
"count": 63368,
"self": 2.4999483490573766,
"children": {
"process_trajectory": {
"total": 122.11179984300088,
"count": 63368,
"self": 121.92924740000126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18255244299962214,
"count": 2,
"self": 0.18255244299962214
}
}
},
"_update_policy": {
"total": 551.5083507229983,
"count": 442,
"self": 349.9119257999864,
"children": {
"TorchPPOOptimizer.update": {
"total": 201.5964249230119,
"count": 22818,
"self": 201.5964249230119
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.879998520365916e-07,
"count": 1,
"self": 7.879998520365916e-07
},
"TrainerController._save_models": {
"total": 0.08317559900024207,
"count": 1,
"self": 0.0016527970001334324,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08152280200010864,
"count": 1,
"self": 0.08152280200010864
}
}
}
}
}
}
}