ppo-PyramidsRND / run_logs /timers.json
JunghwanRo's picture
First Push
a8ca1df
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1442510336637497,
"min": 0.11451829224824905,
"max": 1.3480470180511475,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 4320.60693359375,
"min": 3444.710205078125,
"max": 40894.35546875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989896.0,
"min": 29952.0,
"max": 989896.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.059287749230861664,
"min": -0.11412713676691055,
"max": -0.024523233994841576,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -14.347635269165039,
"min": -27.504640579223633,
"max": -5.959146022796631,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.5606158375740051,
"min": 0.4305139482021332,
"max": 0.6319857835769653,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 135.66903686523438,
"min": 102.03180694580078,
"max": 152.30857849121094,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06926134430036386,
"min": 0.06412677166252058,
"max": 0.07273622407223826,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9696588202050941,
"min": 0.47986848107686303,
"max": 1.0337819476736319,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.0032476753863638986,
"min": 0.0011413444266335795,
"max": 0.009698321192784298,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.04546745540909458,
"min": 0.015082872047207256,
"max": 0.06788824834949009,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.683997438699996e-06,
"min": 7.683997438699996e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010757596414179994,
"min": 0.00010757596414179994,
"max": 0.0035093243302253,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025613,
"min": 0.1025613,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358582,
"min": 1.3886848,
"max": 2.5725582,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002658738699999999,
"min": 0.0002658738699999999,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003722234179999999,
"min": 0.003722234179999999,
"max": 0.11700049253,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.5508722066879272,
"min": 0.42453303933143616,
"max": 0.6225424408912659,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 7.712210655212402,
"min": 3.8207974433898926,
"max": 8.715594291687012,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 882.0322580645161,
"min": 874.8823529411765,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27343.0,
"min": 15984.0,
"max": 32350.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.43073552943045096,
"min": -1.0000000521540642,
"max": -0.4046647572780357,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -13.352801412343979,
"min": -29.884001679718494,
"max": -13.352801412343979,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.43073552943045096,
"min": -1.0000000521540642,
"max": -0.4046647572780357,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -13.352801412343979,
"min": -29.884001679718494,
"max": -13.352801412343979,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 4.832578160950253,
"min": 3.994651288697214,
"max": 12.09012658521533,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 149.80992298945785,
"min": 131.82349252700806,
"max": 193.44202536344528,
"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": "1699647551",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1699649560"
},
"total": 2009.029226489,
"count": 1,
"self": 0.4759235879998869,
"children": {
"run_training.setup": {
"total": 0.04370746700010386,
"count": 1,
"self": 0.04370746700010386
},
"TrainerController.start_learning": {
"total": 2008.509595434,
"count": 1,
"self": 1.3435968530170612,
"children": {
"TrainerController._reset_env": {
"total": 4.683173001000114,
"count": 1,
"self": 4.683173001000114
},
"TrainerController.advance": {
"total": 2002.4097503079831,
"count": 63276,
"self": 1.410307964873482,
"children": {
"env_step": {
"total": 1327.6609585210888,
"count": 63276,
"self": 1193.257055809005,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.5770831470395,
"count": 63276,
"self": 4.759734607023574,
"children": {
"TorchPolicy.evaluate": {
"total": 128.81734854001593,
"count": 62547,
"self": 128.81734854001593
}
}
},
"workers": {
"total": 0.8268195650443886,
"count": 63276,
"self": 0.0,
"children": {
"worker_root": {
"total": 2003.9764994439784,
"count": 63276,
"is_parallel": true,
"self": 930.7434567559608,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0019690950000494922,
"count": 1,
"is_parallel": true,
"self": 0.0006285570000272855,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013405380000222067,
"count": 8,
"is_parallel": true,
"self": 0.0013405380000222067
}
}
},
"UnityEnvironment.step": {
"total": 0.08175849100007326,
"count": 1,
"is_parallel": true,
"self": 0.0006247879998682038,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0009223399999882531,
"count": 1,
"is_parallel": true,
"self": 0.0009223399999882531
},
"communicator.exchange": {
"total": 0.07861025600004723,
"count": 1,
"is_parallel": true,
"self": 0.07861025600004723
},
"steps_from_proto": {
"total": 0.001601107000169577,
"count": 1,
"is_parallel": true,
"self": 0.00033463599993410753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012664710002354695,
"count": 8,
"is_parallel": true,
"self": 0.0012664710002354695
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1073.2330426880176,
"count": 63275,
"is_parallel": true,
"self": 34.079500761044756,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.828734132979434,
"count": 63275,
"is_parallel": true,
"self": 23.828734132979434
},
"communicator.exchange": {
"total": 919.6111114009946,
"count": 63275,
"is_parallel": true,
"self": 919.6111114009946
},
"steps_from_proto": {
"total": 95.71369639299883,
"count": 63275,
"is_parallel": true,
"self": 18.93362607806148,
"children": {
"_process_rank_one_or_two_observation": {
"total": 76.78007031493735,
"count": 506200,
"is_parallel": true,
"self": 76.78007031493735
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 673.3384838220209,
"count": 63276,
"self": 2.68153837802015,
"children": {
"process_trajectory": {
"total": 126.9290633870005,
"count": 63276,
"self": 126.77002365199996,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15903973500053326,
"count": 2,
"self": 0.15903973500053326
}
}
},
"_update_policy": {
"total": 543.7278820570002,
"count": 452,
"self": 332.14034111500155,
"children": {
"TorchPPOOptimizer.update": {
"total": 211.58754094199867,
"count": 22722,
"self": 211.58754094199867
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0009998732130043e-06,
"count": 1,
"self": 1.0009998732130043e-06
},
"TrainerController._save_models": {
"total": 0.07307427099976849,
"count": 1,
"self": 0.0012723379995804862,
"children": {
"RLTrainer._checkpoint": {
"total": 0.071801933000188,
"count": 1,
"self": 0.071801933000188
}
}
}
}
}
}
}