steffel's picture
first trial
5bb98d4
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.5373604893684387,
"min": 0.5303961634635925,
"max": 1.3152064085006714,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 16223.98828125,
"min": 15852.48046875,
"max": 39898.1015625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989975.0,
"min": 29952.0,
"max": 989975.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.3832796812057495,
"min": -0.09921741485595703,
"max": 0.42743149399757385,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 101.952392578125,
"min": -23.812179565429688,
"max": 114.12420654296875,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.029788251966238022,
"min": -0.029788251966238022,
"max": 0.4154064953327179,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -7.923675060272217,
"min": -7.923675060272217,
"max": 98.45133972167969,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06673221637164531,
"min": 0.06450507219276569,
"max": 0.07219515298908975,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9342510292030343,
"min": 0.4911237065038033,
"max": 1.0498681257583895,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014134880150148204,
"min": 0.00016314230072682305,
"max": 0.014134880150148204,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19788832210207485,
"min": 0.0021208499094486997,
"max": 0.19788832210207485,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.698611719542855e-06,
"min": 7.698611719542855e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010778056407359998,
"min": 0.00010778056407359998,
"max": 0.0036320188893270993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256617142857141,
"min": 0.10256617142857141,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4359263999999998,
"min": 1.3691136000000002,
"max": 2.6106729000000004,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002663605257142857,
"min": 0.0002663605257142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037290473599999995,
"min": 0.0037290473599999995,
"max": 0.12108622271000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.010267255827784538,
"min": 0.010267255827784538,
"max": 0.43434271216392517,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.14374157786369324,
"min": 0.14374157786369324,
"max": 3.0403990745544434,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 452.4925373134328,
"min": 407.30882352941177,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30317.0,
"min": 15984.0,
"max": 32969.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.3981969909214262,
"min": -1.0000000521540642,
"max": 1.4101651976073997,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 93.67919839173555,
"min": -32.000001668930054,
"max": 97.30139863491058,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.3981969909214262,
"min": -1.0000000521540642,
"max": 1.4101651976073997,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 93.67919839173555,
"min": -32.000001668930054,
"max": 97.30139863491058,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.048016369453572266,
"min": 0.046964607575226684,
"max": 8.298663738649338,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.2170967533893418,
"min": 3.2170967533893418,
"max": 132.77861981838942,
"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": "1677953039",
"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": "1.22.4",
"end_time_seconds": "1677955138"
},
"total": 2098.731950149,
"count": 1,
"self": 0.4416427289997955,
"children": {
"run_training.setup": {
"total": 0.1124580400000923,
"count": 1,
"self": 0.1124580400000923
},
"TrainerController.start_learning": {
"total": 2098.17784938,
"count": 1,
"self": 1.2341701859945715,
"children": {
"TrainerController._reset_env": {
"total": 6.207762624999987,
"count": 1,
"self": 6.207762624999987
},
"TrainerController.advance": {
"total": 2090.651149235006,
"count": 63420,
"self": 1.3519664210648443,
"children": {
"env_step": {
"total": 1357.8515068980143,
"count": 63420,
"self": 1247.081767976084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 109.97601529293433,
"count": 63420,
"self": 4.6381676539049295,
"children": {
"TorchPolicy.evaluate": {
"total": 105.3378476390294,
"count": 62556,
"self": 36.1099438780775,
"children": {
"TorchPolicy.sample_actions": {
"total": 69.2279037609519,
"count": 62556,
"self": 69.2279037609519
}
}
}
}
},
"workers": {
"total": 0.7937236289960765,
"count": 63420,
"self": 0.0,
"children": {
"worker_root": {
"total": 2093.9109387800404,
"count": 63420,
"is_parallel": true,
"self": 956.0386994750102,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017898119999699702,
"count": 1,
"is_parallel": true,
"self": 0.0006573630000730191,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011324489998969511,
"count": 8,
"is_parallel": true,
"self": 0.0011324489998969511
}
}
},
"UnityEnvironment.step": {
"total": 0.046676848000061,
"count": 1,
"is_parallel": true,
"self": 0.0005110159997911978,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045504300010179577,
"count": 1,
"is_parallel": true,
"self": 0.00045504300010179577
},
"communicator.exchange": {
"total": 0.04411516000004667,
"count": 1,
"is_parallel": true,
"self": 0.04411516000004667
},
"steps_from_proto": {
"total": 0.0015956290001213347,
"count": 1,
"is_parallel": true,
"self": 0.00040382099996350007,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011918080001578346,
"count": 8,
"is_parallel": true,
"self": 0.0011918080001578346
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1137.8722393050302,
"count": 63419,
"is_parallel": true,
"self": 30.573800557932827,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.243576933043187,
"count": 63419,
"is_parallel": true,
"self": 22.243576933043187
},
"communicator.exchange": {
"total": 995.3495769730087,
"count": 63419,
"is_parallel": true,
"self": 995.3495769730087
},
"steps_from_proto": {
"total": 89.70528484104557,
"count": 63419,
"is_parallel": true,
"self": 21.0284950618352,
"children": {
"_process_rank_one_or_two_observation": {
"total": 68.67678977921037,
"count": 507352,
"is_parallel": true,
"self": 68.67678977921037
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 731.4476759159265,
"count": 63420,
"self": 2.27405719991134,
"children": {
"process_trajectory": {
"total": 158.90977314901056,
"count": 63420,
"self": 158.7282390810101,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18153406800047378,
"count": 2,
"self": 0.18153406800047378
}
}
},
"_update_policy": {
"total": 570.2638455670046,
"count": 445,
"self": 217.8868000310547,
"children": {
"TorchPPOOptimizer.update": {
"total": 352.37704553594995,
"count": 22845,
"self": 352.37704553594995
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.550000529794488e-07,
"count": 1,
"self": 8.550000529794488e-07
},
"TrainerController._save_models": {
"total": 0.08476647899988166,
"count": 1,
"self": 0.001411243999882572,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08335523499999908,
"count": 1,
"self": 0.08335523499999908
}
}
}
}
}
}
}