ppo-PyramidsRND / run_logs /timers.json
DarkRodry's picture
First Push
786875a
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3985706865787506,
"min": 0.3985706865787506,
"max": 1.4191246032714844,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 12020.8916015625,
"min": 12020.8916015625,
"max": 43050.5625,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989981.0,
"min": 29952.0,
"max": 989981.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989981.0,
"min": 29952.0,
"max": 989981.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4726175367832184,
"min": -0.1024954691529274,
"max": 0.5100879669189453,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 130.44244384765625,
"min": -24.70140838623047,
"max": 137.7237548828125,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.02270619384944439,
"min": -0.00255902879871428,
"max": 0.4762710928916931,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.266909599304199,
"min": -0.6832606792449951,
"max": 112.87625122070312,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06924074453542875,
"min": 0.06456407504447272,
"max": 0.07370579460430669,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9693704234960024,
"min": 0.49695873260263873,
"max": 1.0318811244602937,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015128493035652873,
"min": 0.0003230029049313533,
"max": 0.01576459093762207,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2117989024991402,
"min": 0.004522040669038946,
"max": 0.22070427312670898,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.543597485499997e-06,
"min": 7.543597485499997e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010561036479699995,
"min": 0.00010561036479699995,
"max": 0.0034902649365783993,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10251450000000002,
"min": 0.10251450000000002,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4352030000000002,
"min": 1.3886848,
"max": 2.4859992,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026119855,
"min": 0.00026119855,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0036567797,
"min": 0.0036567797,
"max": 0.11635581784000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.00882726814597845,
"min": 0.00882726814597845,
"max": 0.4087875187397003,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12358175218105316,
"min": 0.12358175218105316,
"max": 2.8615126609802246,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 358.8953488372093,
"min": 358.8953488372093,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30865.0,
"min": 15984.0,
"max": 32252.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5015232438264892,
"min": -1.0000000521540642,
"max": 1.5575279806057611,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 129.13099896907806,
"min": -30.278801679611206,
"max": 129.13099896907806,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5015232438264892,
"min": -1.0000000521540642,
"max": 1.5575279806057611,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 129.13099896907806,
"min": -30.278801679611206,
"max": 129.13099896907806,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03333737779757939,
"min": 0.03333737779757939,
"max": 8.775430575944483,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.867014490591828,
"min": 2.867014490591828,
"max": 140.40688921511173,
"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": "1692627043",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1692629324"
},
"total": 2280.279735013,
"count": 1,
"self": 0.48270076399967365,
"children": {
"run_training.setup": {
"total": 0.038792851999915,
"count": 1,
"self": 0.038792851999915
},
"TrainerController.start_learning": {
"total": 2279.7582413970003,
"count": 1,
"self": 1.3553908919861897,
"children": {
"TrainerController._reset_env": {
"total": 4.135371060000125,
"count": 1,
"self": 4.135371060000125
},
"TrainerController.advance": {
"total": 2274.170984385014,
"count": 63699,
"self": 1.3653294569935497,
"children": {
"env_step": {
"total": 1602.712615742008,
"count": 63699,
"self": 1493.8564982629646,
"children": {
"SubprocessEnvManager._take_step": {
"total": 108.03049448603315,
"count": 63699,
"self": 4.619126763048371,
"children": {
"TorchPolicy.evaluate": {
"total": 103.41136772298478,
"count": 62549,
"self": 103.41136772298478
}
}
},
"workers": {
"total": 0.8256229930102563,
"count": 63699,
"self": 0.0,
"children": {
"worker_root": {
"total": 2274.7983099409416,
"count": 63699,
"is_parallel": true,
"self": 895.1291463410525,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017739640002218948,
"count": 1,
"is_parallel": true,
"self": 0.0005477920012708637,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012261719989510311,
"count": 8,
"is_parallel": true,
"self": 0.0012261719989510311
}
}
},
"UnityEnvironment.step": {
"total": 0.04513697599986699,
"count": 1,
"is_parallel": true,
"self": 0.0005804350003018044,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00047696899991933606,
"count": 1,
"is_parallel": true,
"self": 0.00047696899991933606
},
"communicator.exchange": {
"total": 0.042253112999787845,
"count": 1,
"is_parallel": true,
"self": 0.042253112999787845
},
"steps_from_proto": {
"total": 0.001826458999858005,
"count": 1,
"is_parallel": true,
"self": 0.0003589800003283017,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014674789995297033,
"count": 8,
"is_parallel": true,
"self": 0.0014674789995297033
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1379.669163599889,
"count": 63698,
"is_parallel": true,
"self": 34.00508180578936,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.93117980602392,
"count": 63698,
"is_parallel": true,
"self": 22.93117980602392
},
"communicator.exchange": {
"total": 1217.6486929560442,
"count": 63698,
"is_parallel": true,
"self": 1217.6486929560442
},
"steps_from_proto": {
"total": 105.0842090320316,
"count": 63698,
"is_parallel": true,
"self": 20.43065279425582,
"children": {
"_process_rank_one_or_two_observation": {
"total": 84.65355623777577,
"count": 509584,
"is_parallel": true,
"self": 84.65355623777577
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 670.0930391860124,
"count": 63699,
"self": 2.584255004096576,
"children": {
"process_trajectory": {
"total": 111.51345027891739,
"count": 63699,
"self": 111.30475993491746,
"children": {
"RLTrainer._checkpoint": {
"total": 0.20869034399993325,
"count": 2,
"self": 0.20869034399993325
}
}
},
"_update_policy": {
"total": 555.9953339029985,
"count": 449,
"self": 362.86969991903106,
"children": {
"TorchPPOOptimizer.update": {
"total": 193.12563398396742,
"count": 22794,
"self": 193.12563398396742
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0450003173900768e-06,
"count": 1,
"self": 1.0450003173900768e-06
},
"TrainerController._save_models": {
"total": 0.09649401499973465,
"count": 1,
"self": 0.0019161269992764574,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09457788800045819,
"count": 1,
"self": 0.09457788800045819
}
}
}
}
}
}
}