ppo-PyramidsRND / run_logs /timers.json
gchindemi's picture
First Push
07ca238
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4095015227794647,
"min": 0.40463441610336304,
"max": 1.3931279182434082,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12199.869140625,
"min": 12126.083984375,
"max": 42261.9296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989978.0,
"min": 29952.0,
"max": 989978.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989978.0,
"min": 29952.0,
"max": 989978.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5168585181236267,
"min": -0.20790404081344604,
"max": 0.5236042141914368,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 141.61923217773438,
"min": -49.273258209228516,
"max": 141.61923217773438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.03587096557021141,
"min": -0.03587096557021141,
"max": 0.5450994372367859,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -9.828644752502441,
"min": -9.828644752502441,
"max": 129.18856811523438,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06980910734550673,
"min": 0.06510039390940663,
"max": 0.07245275906253872,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9773275028370941,
"min": 0.48942670842931046,
"max": 1.0437538943854938,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014090034974201226,
"min": 0.0004757961505256362,
"max": 0.01547784804942138,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.19726048963881718,
"min": 0.00618534995683327,
"max": 0.23216772074132072,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.563590335978571e-06,
"min": 7.563590335978571e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001058902647037,
"min": 0.0001058902647037,
"max": 0.0035069213310262998,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1025211642857143,
"min": 0.1025211642857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352963,
"min": 1.3886848,
"max": 2.5728377,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026186431214285724,
"min": 0.00026186431214285724,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036661003700000014,
"min": 0.0036661003700000014,
"max": 0.11692047263,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.012259522452950478,
"min": 0.012259522452950478,
"max": 0.637045681476593,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.17163331806659698,
"min": 0.17163331806659698,
"max": 4.459319591522217,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 368.9512195121951,
"min": 368.9512195121951,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30254.0,
"min": 15984.0,
"max": 32795.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5090731522295533,
"min": -1.0000000521540642,
"max": 1.5809130234562832,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 123.74399848282337,
"min": -29.695401653647423,
"max": 126.78779824078083,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5090731522295533,
"min": -1.0000000521540642,
"max": 1.5809130234562832,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 123.74399848282337,
"min": -29.695401653647423,
"max": 126.78779824078083,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.047463823758845114,
"min": 0.047463823758845114,
"max": 12.869656275957823,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.8920335482252995,
"min": 3.8920335482252995,
"max": 205.91450041532516,
"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": "1702199255",
"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": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702201594"
},
"total": 2338.700812102,
"count": 1,
"self": 0.4924779530001615,
"children": {
"run_training.setup": {
"total": 0.06575299000002133,
"count": 1,
"self": 0.06575299000002133
},
"TrainerController.start_learning": {
"total": 2338.1425811589997,
"count": 1,
"self": 1.6074512479635814,
"children": {
"TrainerController._reset_env": {
"total": 4.0240669880000155,
"count": 1,
"self": 4.0240669880000155
},
"TrainerController.advance": {
"total": 2332.427901337036,
"count": 63675,
"self": 1.685176971043802,
"children": {
"env_step": {
"total": 1657.386024180972,
"count": 63675,
"self": 1509.4195320269891,
"children": {
"SubprocessEnvManager._take_step": {
"total": 146.95402555296027,
"count": 63675,
"self": 5.162059244965178,
"children": {
"TorchPolicy.evaluate": {
"total": 141.7919663079951,
"count": 62565,
"self": 141.7919663079951
}
}
},
"workers": {
"total": 1.012466601022652,
"count": 63675,
"self": 0.0,
"children": {
"worker_root": {
"total": 2332.968775302944,
"count": 63675,
"is_parallel": true,
"self": 954.1968561019476,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00555824200000643,
"count": 1,
"is_parallel": true,
"self": 0.004171780999968178,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013864610000382527,
"count": 8,
"is_parallel": true,
"self": 0.0013864610000382527
}
}
},
"UnityEnvironment.step": {
"total": 0.08785090499998205,
"count": 1,
"is_parallel": true,
"self": 0.0006573189999699025,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005169160000377815,
"count": 1,
"is_parallel": true,
"self": 0.0005169160000377815
},
"communicator.exchange": {
"total": 0.08484912099999065,
"count": 1,
"is_parallel": true,
"self": 0.08484912099999065
},
"steps_from_proto": {
"total": 0.0018275489999837191,
"count": 1,
"is_parallel": true,
"self": 0.0003865389999191393,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014410100000645798,
"count": 8,
"is_parallel": true,
"self": 0.0014410100000645798
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1378.7719192009963,
"count": 63674,
"is_parallel": true,
"self": 37.02415554704453,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.95664666296392,
"count": 63674,
"is_parallel": true,
"self": 24.95664666296392
},
"communicator.exchange": {
"total": 1212.0872755219973,
"count": 63674,
"is_parallel": true,
"self": 1212.0872755219973
},
"steps_from_proto": {
"total": 104.70384146899045,
"count": 63674,
"is_parallel": true,
"self": 21.487579887067113,
"children": {
"_process_rank_one_or_two_observation": {
"total": 83.21626158192333,
"count": 509392,
"is_parallel": true,
"self": 83.21626158192333
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 673.3567001850201,
"count": 63675,
"self": 3.1064288460472653,
"children": {
"process_trajectory": {
"total": 133.3139906039678,
"count": 63675,
"self": 133.13918685896806,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1748037449997355,
"count": 2,
"self": 0.1748037449997355
}
}
},
"_update_policy": {
"total": 536.9362807350051,
"count": 453,
"self": 322.08731683602787,
"children": {
"TorchPPOOptimizer.update": {
"total": 214.84896389897722,
"count": 22794,
"self": 214.84896389897722
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.390002221858595e-07,
"count": 1,
"self": 8.390002221858595e-07
},
"TrainerController._save_models": {
"total": 0.08316074699996534,
"count": 1,
"self": 0.0012302260001888499,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08193052099977649,
"count": 1,
"self": 0.08193052099977649
}
}
}
}
}
}
}