rezadadfar's picture
First Push
cd0f42b
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.43269777297973633,
"min": 0.43269777297973633,
"max": 1.371383786201477,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13181.705078125,
"min": 13181.705078125,
"max": 41602.296875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989964.0,
"min": 29952.0,
"max": 989964.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5644271969795227,
"min": -0.08764486759901047,
"max": 0.5962366461753845,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 156.9107666015625,
"min": -21.210058212280273,
"max": 167.54249572753906,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.024280712008476257,
"min": -0.025254247710108757,
"max": 0.7589455246925354,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 6.750038146972656,
"min": -6.919663906097412,
"max": 179.87008666992188,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07187978142645167,
"min": 0.06446054169208044,
"max": 0.07276190655461871,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 1.0063169399703233,
"min": 0.509333345882331,
"max": 1.0538843020028663,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.017543129561610322,
"min": 0.00027802690595879037,
"max": 0.01829602527695464,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.24560381386254448,
"min": 0.0038923766834230654,
"max": 0.25614435387736495,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.632654598671428e-06,
"min": 7.632654598671428e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.0001068571643814,
"min": 0.0001068571643814,
"max": 0.0034928023357326003,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10254418571428571,
"min": 0.10254418571428571,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4356186,
"min": 1.3886848,
"max": 2.527412000000001,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.00026416415285714285,
"min": 0.00026416415285714285,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.00369829814,
"min": 0.00369829814,
"max": 0.11644031326000001,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.014289124868810177,
"min": 0.014289124868810177,
"max": 0.696894109249115,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.20004774630069733,
"min": 0.20004774630069733,
"max": 4.87825870513916,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 334.3804347826087,
"min": 303.8019801980198,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30763.0,
"min": 15984.0,
"max": 32757.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6438782430537369,
"min": -1.0000000521540642,
"max": 1.6538845163952445,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 151.2367983609438,
"min": -30.77900169789791,
"max": 165.31419833749533,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6438782430537369,
"min": -1.0000000521540642,
"max": 1.6538845163952445,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 151.2367983609438,
"min": -30.77900169789791,
"max": 165.31419833749533,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.04913479718253138,
"min": 0.04577270215473224,
"max": 14.993331799283624,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 4.520401340792887,
"min": 4.379859752638367,
"max": 239.89330878853798,
"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": "1703984879",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703987082"
},
"total": 2203.7050966410006,
"count": 1,
"self": 0.9287682379999751,
"children": {
"run_training.setup": {
"total": 0.07198636900011479,
"count": 1,
"self": 0.07198636900011479
},
"TrainerController.start_learning": {
"total": 2202.7043420340005,
"count": 1,
"self": 1.28955770093944,
"children": {
"TrainerController._reset_env": {
"total": 2.2628496709999126,
"count": 1,
"self": 2.2628496709999126
},
"TrainerController.advance": {
"total": 2199.0324727370603,
"count": 63795,
"self": 1.3718093688648878,
"children": {
"env_step": {
"total": 1565.677520177051,
"count": 63795,
"self": 1438.9510552421903,
"children": {
"SubprocessEnvManager._take_step": {
"total": 125.93731404285018,
"count": 63795,
"self": 4.561828710750888,
"children": {
"TorchPolicy.evaluate": {
"total": 121.37548533209929,
"count": 62564,
"self": 121.37548533209929
}
}
},
"workers": {
"total": 0.7891508920106389,
"count": 63795,
"self": 0.0,
"children": {
"worker_root": {
"total": 2197.7586115720565,
"count": 63795,
"is_parallel": true,
"self": 875.5834830330823,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0017043299999386363,
"count": 1,
"is_parallel": true,
"self": 0.0005121619997225935,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011921680002160429,
"count": 8,
"is_parallel": true,
"self": 0.0011921680002160429
}
}
},
"UnityEnvironment.step": {
"total": 0.05379153800004133,
"count": 1,
"is_parallel": true,
"self": 0.0006080959997234459,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005412160003288591,
"count": 1,
"is_parallel": true,
"self": 0.0005412160003288591
},
"communicator.exchange": {
"total": 0.05098719900024662,
"count": 1,
"is_parallel": true,
"self": 0.05098719900024662
},
"steps_from_proto": {
"total": 0.0016550269997424039,
"count": 1,
"is_parallel": true,
"self": 0.0003480849991319701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013069420006104338,
"count": 8,
"is_parallel": true,
"self": 0.0013069420006104338
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1322.1751285389741,
"count": 63794,
"is_parallel": true,
"self": 34.914668810930834,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.189073132123667,
"count": 63794,
"is_parallel": true,
"self": 24.189073132123667
},
"communicator.exchange": {
"total": 1165.3040251779203,
"count": 63794,
"is_parallel": true,
"self": 1165.3040251779203
},
"steps_from_proto": {
"total": 97.76736141799938,
"count": 63794,
"is_parallel": true,
"self": 19.252387028197973,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.51497438980141,
"count": 510352,
"is_parallel": true,
"self": 78.51497438980141
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 631.9831431911443,
"count": 63795,
"self": 2.470314573151427,
"children": {
"process_trajectory": {
"total": 125.1846878289939,
"count": 63795,
"self": 124.96146760299371,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2232202260001941,
"count": 2,
"self": 0.2232202260001941
}
}
},
"_update_policy": {
"total": 504.328140788999,
"count": 452,
"self": 299.1198332430454,
"children": {
"TorchPPOOptimizer.update": {
"total": 205.20830754595363,
"count": 22842,
"self": 205.20830754595363
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.184000211651437e-06,
"count": 1,
"self": 1.184000211651437e-06
},
"TrainerController._save_models": {
"total": 0.11946074100069382,
"count": 1,
"self": 0.002035024001088459,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11742571699960536,
"count": 1,
"self": 0.11742571699960536
}
}
}
}
}
}
}