svetaU's picture
The model ...
c8e7350 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.6589476466178894,
"min": 0.6589476466178894,
"max": 1.4170805215835571,
"count": 10
},
"Pyramids.Policy.Entropy.sum": {
"value": 19673.541015625,
"min": 19673.541015625,
"max": 42988.5546875,
"count": 10
},
"Pyramids.Step.mean": {
"value": 299943.0,
"min": 29952.0,
"max": 299943.0,
"count": 10
},
"Pyramids.Step.sum": {
"value": 299943.0,
"min": 29952.0,
"max": 299943.0,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": -0.07627826184034348,
"min": -0.1051979809999466,
"max": 0.08111945539712906,
"count": 10
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": -18.30678367614746,
"min": -25.352712631225586,
"max": 19.225311279296875,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.041035246104002,
"min": 0.041035246104002,
"max": 0.5827386379241943,
"count": 10
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 9.848459243774414,
"min": 9.848459243774414,
"max": 138.1090545654297,
"count": 10
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.07023418793507394,
"min": 0.0659977481817062,
"max": 0.07123017356193093,
"count": 10
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9130444431559611,
"min": 0.48441105684402314,
"max": 0.9744470087287804,
"count": 10
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.002341259585013319,
"min": 0.00015470885853479492,
"max": 0.042207692784350145,
"count": 10
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.030436374605173146,
"min": 0.001856506302417539,
"max": 0.295453849490451,
"count": 10
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5517556365974356e-05,
"min": 1.5517556365974356e-05,
"max": 0.0002838354339596191,
"count": 10
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00020172823275766663,
"min": 0.00020172823275766663,
"max": 0.002707216297594666,
"count": 10
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10517248717948718,
"min": 0.10517248717948718,
"max": 0.19461180952380958,
"count": 10
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.3672423333333334,
"min": 1.362282666666667,
"max": 2.1477346666666666,
"count": 10
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0005267314692307692,
"min": 0.0005267314692307692,
"max": 0.00946171977142857,
"count": 10
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0068475090999999995,
"min": 0.0068475090999999995,
"max": 0.09027029280000001,
"count": 10
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.036779049783945084,
"min": 0.036779049783945084,
"max": 0.6622408032417297,
"count": 10
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.4781276285648346,
"min": 0.4781276285648346,
"max": 4.635685443878174,
"count": 10
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 949.2903225806451,
"min": 918.4347826086956,
"max": 999.0,
"count": 10
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 29428.0,
"min": 15984.0,
"max": 32664.0,
"count": 10
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": -0.6919548852789786,
"min": -1.0000000521540642,
"max": -0.6582261294774387,
"count": 10
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": -21.45060144364834,
"min": -30.994801588356495,
"max": -15.13920097798109,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": -0.6919548852789786,
"min": -1.0000000521540642,
"max": -0.6582261294774387,
"count": 10
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": -21.45060144364834,
"min": -30.994801588356495,
"max": -15.13920097798109,
"count": 10
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.3642648289040212,
"min": 0.3642648289040212,
"max": 14.61310539394617,
"count": 10
},
"Pyramids.Policy.RndReward.sum": {
"value": 11.292209696024656,
"min": 9.186005219817162,
"max": 233.80968630313873,
"count": 10
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1726857892",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1726858842"
},
"total": 949.815996475,
"count": 1,
"self": 0.5853102480000416,
"children": {
"run_training.setup": {
"total": 0.06996678799987421,
"count": 1,
"self": 0.06996678799987421
},
"TrainerController.start_learning": {
"total": 949.1607194390001,
"count": 1,
"self": 0.6989864650020081,
"children": {
"TrainerController._reset_env": {
"total": 2.292648053999983,
"count": 1,
"self": 2.292648053999983
},
"TrainerController.advance": {
"total": 946.0741315509977,
"count": 18844,
"self": 0.7711623710436015,
"children": {
"env_step": {
"total": 593.8782932239999,
"count": 18844,
"self": 540.927633974027,
"children": {
"SubprocessEnvManager._take_step": {
"total": 52.536357583000836,
"count": 18844,
"self": 2.16491420099851,
"children": {
"TorchPolicy.evaluate": {
"total": 50.371443382002326,
"count": 18769,
"self": 50.371443382002326
}
}
},
"workers": {
"total": 0.41430166697205095,
"count": 18844,
"self": 0.0,
"children": {
"worker_root": {
"total": 947.0959101180022,
"count": 18844,
"is_parallel": true,
"self": 462.6763899470236,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0031568270001116616,
"count": 1,
"is_parallel": true,
"self": 0.0011399990003155835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002016827999796078,
"count": 8,
"is_parallel": true,
"self": 0.002016827999796078
}
}
},
"UnityEnvironment.step": {
"total": 0.061128644999826065,
"count": 1,
"is_parallel": true,
"self": 0.0007484579998617846,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005746550000367279,
"count": 1,
"is_parallel": true,
"self": 0.0005746550000367279
},
"communicator.exchange": {
"total": 0.05719423999994433,
"count": 1,
"is_parallel": true,
"self": 0.05719423999994433
},
"steps_from_proto": {
"total": 0.002611291999983223,
"count": 1,
"is_parallel": true,
"self": 0.0004596700000547571,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002151621999928466,
"count": 8,
"is_parallel": true,
"self": 0.002151621999928466
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 484.41952017097856,
"count": 18843,
"is_parallel": true,
"self": 15.079458153026053,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.546275807965003,
"count": 18843,
"is_parallel": true,
"self": 9.546275807965003
},
"communicator.exchange": {
"total": 421.299370772005,
"count": 18843,
"is_parallel": true,
"self": 421.299370772005
},
"steps_from_proto": {
"total": 38.494415437982525,
"count": 18843,
"is_parallel": true,
"self": 8.312281962927727,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.182133475054798,
"count": 150744,
"is_parallel": true,
"self": 30.182133475054798
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 351.42467595595417,
"count": 18844,
"self": 1.1040707449458296,
"children": {
"process_trajectory": {
"total": 48.39056430701203,
"count": 18844,
"self": 48.39056430701203
},
"_update_policy": {
"total": 301.9300409039963,
"count": 119,
"self": 120.85855598100238,
"children": {
"TorchPPOOptimizer.update": {
"total": 181.07148492299393,
"count": 6849,
"self": 181.07148492299393
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1880001693498343e-06,
"count": 1,
"self": 1.1880001693498343e-06
},
"TrainerController._save_models": {
"total": 0.09495218100028069,
"count": 1,
"self": 0.0020042390001435706,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09294794200013712,
"count": 1,
"self": 0.09294794200013712
}
}
}
}
}
}
}