ppornd-Pyramids / run_logs /timers.json
dn-gh's picture
upload ppo agent
aa21265
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.31234657764434814,
"min": 0.31234657764434814,
"max": 1.3495274782180786,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 9320.421875,
"min": 9320.421875,
"max": 40939.265625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989980.0,
"min": 29952.0,
"max": 989980.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5284985303878784,
"min": -0.10383376479148865,
"max": 0.6411994099617004,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 144.80859375,
"min": -25.023937225341797,
"max": 184.02423095703125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0076410952024161816,
"min": 0.0076410952024161816,
"max": 0.33276498317718506,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.0936601161956787,
"min": 2.0936601161956787,
"max": 80.19635772705078,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06685805086653643,
"min": 0.06496131510650313,
"max": 0.07516892390978783,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.93601271213151,
"min": 0.47875424998597615,
"max": 1.0388456118252019,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016307455232585078,
"min": 0.001060984929496477,
"max": 0.017284731899313295,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22830437325619107,
"min": 0.012731819153957723,
"max": 0.24198624659038614,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.470311795642858e-06,
"min": 7.470311795642858e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010458436513900001,
"min": 0.00010458436513900001,
"max": 0.0033828155723949,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10249007142857143,
"min": 0.10249007142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.434861,
"min": 1.3886848,
"max": 2.5276051,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002587581357142857,
"min": 0.0002587581357142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036226139,
"min": 0.0036226139,
"max": 0.11278774949,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.01272207498550415,
"min": 0.01272207498550415,
"max": 0.5273298621177673,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.1781090497970581,
"min": 0.1781090497970581,
"max": 3.6913092136383057,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 353.6511627906977,
"min": 285.873786407767,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30414.0,
"min": 15984.0,
"max": 33451.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5023788013878991,
"min": -1.0000000521540642,
"max": 1.6752834775783483,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 127.70219811797142,
"min": -29.759601704776287,
"max": 172.55419819056988,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5023788013878991,
"min": -1.0000000521540642,
"max": 1.6752834775783483,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 127.70219811797142,
"min": -29.759601704776287,
"max": 172.55419819056988,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.047036507857881264,
"min": 0.04246114741265258,
"max": 10.060094933956861,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.9981031679199077,
"min": 3.9981031679199077,
"max": 160.96151894330978,
"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": "1675535930",
"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": "1675538104"
},
"total": 2173.800892608,
"count": 1,
"self": 0.4428209070001685,
"children": {
"run_training.setup": {
"total": 0.10603897800001505,
"count": 1,
"self": 0.10603897800001505
},
"TrainerController.start_learning": {
"total": 2173.252032723,
"count": 1,
"self": 1.4458092500262865,
"children": {
"TrainerController._reset_env": {
"total": 9.949615282999957,
"count": 1,
"self": 9.949615282999957
},
"TrainerController.advance": {
"total": 2161.7691920229745,
"count": 63963,
"self": 1.4632480539958124,
"children": {
"env_step": {
"total": 1496.6768940449886,
"count": 63963,
"self": 1378.8651198820091,
"children": {
"SubprocessEnvManager._take_step": {
"total": 116.92508761099498,
"count": 63963,
"self": 4.827524987960487,
"children": {
"TorchPolicy.evaluate": {
"total": 112.09756262303449,
"count": 62566,
"self": 37.358783033985674,
"children": {
"TorchPolicy.sample_actions": {
"total": 74.73877958904882,
"count": 62566,
"self": 74.73877958904882
}
}
}
}
},
"workers": {
"total": 0.8866865519844396,
"count": 63963,
"self": 0.0,
"children": {
"worker_root": {
"total": 2168.1077772359704,
"count": 63963,
"is_parallel": true,
"self": 900.1514765030568,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005856971999946836,
"count": 1,
"is_parallel": true,
"self": 0.0033058819992675126,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025510900006793236,
"count": 8,
"is_parallel": true,
"self": 0.0025510900006793236
}
}
},
"UnityEnvironment.step": {
"total": 0.053690403000018705,
"count": 1,
"is_parallel": true,
"self": 0.0005863339997631556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045145500007492956,
"count": 1,
"is_parallel": true,
"self": 0.00045145500007492956
},
"communicator.exchange": {
"total": 0.045563305000086984,
"count": 1,
"is_parallel": true,
"self": 0.045563305000086984
},
"steps_from_proto": {
"total": 0.007089309000093635,
"count": 1,
"is_parallel": true,
"self": 0.0006093029999192368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.006480006000174399,
"count": 8,
"is_parallel": true,
"self": 0.006480006000174399
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1267.9563007329136,
"count": 63962,
"is_parallel": true,
"self": 29.321045706782797,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.074557244040307,
"count": 63962,
"is_parallel": true,
"self": 24.074557244040307
},
"communicator.exchange": {
"total": 1115.0257166360545,
"count": 63962,
"is_parallel": true,
"self": 1115.0257166360545
},
"steps_from_proto": {
"total": 99.53498114603599,
"count": 63962,
"is_parallel": true,
"self": 24.243327427063605,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.29165371897238,
"count": 511696,
"is_parallel": true,
"self": 75.29165371897238
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 663.6290499239901,
"count": 63963,
"self": 2.610966622007709,
"children": {
"process_trajectory": {
"total": 152.75623073298357,
"count": 63963,
"self": 152.54854907798335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20768165500021496,
"count": 2,
"self": 0.20768165500021496
}
}
},
"_update_policy": {
"total": 508.26185256899885,
"count": 451,
"self": 188.56889329400155,
"children": {
"TorchPPOOptimizer.update": {
"total": 319.6929592749973,
"count": 22800,
"self": 319.6929592749973
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.389997674385086e-07,
"count": 1,
"self": 8.389997674385086e-07
},
"TrainerController._save_models": {
"total": 0.087415327999679,
"count": 1,
"self": 0.0014765979999538104,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08593872999972518,
"count": 1,
"self": 0.08593872999972518
}
}
}
}
}
}
}