ppo-Pyramids / run_logs /timers.json
HanliChu's picture
Pushed the model.
0a27896 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1400655210018158,
"min": 0.13757012784481049,
"max": 1.4607993364334106,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4172.83203125,
"min": 4149.115234375,
"max": 44314.80859375,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999894.0,
"min": 29952.0,
"max": 2999894.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999894.0,
"min": 29952.0,
"max": 2999894.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.81910640001297,
"min": -0.10586967319250107,
"max": 0.8616036772727966,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 241.63638305664062,
"min": -25.514591217041016,
"max": 259.34271240234375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.0012309565208852291,
"min": -0.0047210389748215675,
"max": 0.4278755486011505,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 0.36313217878341675,
"min": -1.3927065134048462,
"max": 101.40650177001953,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06875650944117802,
"min": 0.06475493951693455,
"max": 0.07395582562118458,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9625911321764923,
"min": 0.49227781557670697,
"max": 1.1093373843177687,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.01623647818351634,
"min": 0.0002478167770441368,
"max": 0.016665379125305326,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.22731069456922876,
"min": 0.0032216181015737788,
"max": 0.24229611830977615,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5141209238976224e-06,
"min": 1.5141209238976224e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.1197692934566715e-05,
"min": 2.1197692934566715e-05,
"max": 0.0038924546025151997,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1005046738095238,
"min": 0.1005046738095238,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4070654333333332,
"min": 1.3962282666666668,
"max": 2.7974848000000008,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.041691357142869e-05,
"min": 6.041691357142869e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008458367900000017,
"min": 0.0008458367900000017,
"max": 0.12976873152,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.009070133790373802,
"min": 0.0089982645586133,
"max": 0.47463229298591614,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.12698186933994293,
"min": 0.12597569823265076,
"max": 3.3224260807037354,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 230.15833333333333,
"min": 212.90845070422534,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27619.0,
"min": 15984.0,
"max": 32872.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.7531699864814678,
"min": -1.0000000521540642,
"max": 1.778999978690657,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 210.38039837777615,
"min": -31.994001641869545,
"max": 253.64299838989973,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.7531699864814678,
"min": -1.0000000521540642,
"max": 1.778999978690657,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 210.38039837777615,
"min": -31.994001641869545,
"max": 253.64299838989973,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.021996843544548027,
"min": 0.020545900398800214,
"max": 10.397399662062526,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.6396212253457634,
"min": 2.6396212253457634,
"max": 166.3583945930004,
"count": 100
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1711453185",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711460218"
},
"total": 7033.065106619,
"count": 1,
"self": 0.8540321300006326,
"children": {
"run_training.setup": {
"total": 0.04869089299972984,
"count": 1,
"self": 0.04869089299972984
},
"TrainerController.start_learning": {
"total": 7032.162383596,
"count": 1,
"self": 3.9724685611399764,
"children": {
"TrainerController._reset_env": {
"total": 2.172382175000166,
"count": 1,
"self": 2.172382175000166
},
"TrainerController.advance": {
"total": 7025.88488963686,
"count": 194417,
"self": 4.144406190884183,
"children": {
"env_step": {
"total": 5152.356212544695,
"count": 194417,
"self": 4764.913823263869,
"children": {
"SubprocessEnvManager._take_step": {
"total": 384.98302192011624,
"count": 194417,
"self": 13.81035440828191,
"children": {
"TorchPolicy.evaluate": {
"total": 371.17266751183433,
"count": 187562,
"self": 371.17266751183433
}
}
},
"workers": {
"total": 2.4593673607100754,
"count": 194417,
"self": 0.0,
"children": {
"worker_root": {
"total": 7016.524473096083,
"count": 194417,
"is_parallel": true,
"self": 2606.7135365571094,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022589889999835577,
"count": 1,
"is_parallel": true,
"self": 0.0006203779998941172,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016386110000894405,
"count": 8,
"is_parallel": true,
"self": 0.0016386110000894405
}
}
},
"UnityEnvironment.step": {
"total": 0.04805504999967525,
"count": 1,
"is_parallel": true,
"self": 0.0006235199994080176,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045637200037162984,
"count": 1,
"is_parallel": true,
"self": 0.00045637200037162984
},
"communicator.exchange": {
"total": 0.04540449099977195,
"count": 1,
"is_parallel": true,
"self": 0.04540449099977195
},
"steps_from_proto": {
"total": 0.001570667000123649,
"count": 1,
"is_parallel": true,
"self": 0.0003279570000813692,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012427100000422797,
"count": 8,
"is_parallel": true,
"self": 0.0012427100000422797
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4409.810936538974,
"count": 194416,
"is_parallel": true,
"self": 104.02848758010168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 69.64849082981527,
"count": 194416,
"is_parallel": true,
"self": 69.64849082981527
},
"communicator.exchange": {
"total": 3941.6140566360173,
"count": 194416,
"is_parallel": true,
"self": 3941.6140566360173
},
"steps_from_proto": {
"total": 294.51990149303947,
"count": 194416,
"is_parallel": true,
"self": 58.917539256043256,
"children": {
"_process_rank_one_or_two_observation": {
"total": 235.6023622369962,
"count": 1555328,
"is_parallel": true,
"self": 235.6023622369962
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1869.3842709012802,
"count": 194417,
"self": 8.166629575114712,
"children": {
"process_trajectory": {
"total": 382.6570993861492,
"count": 194417,
"self": 382.0261032751505,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6309961109986943,
"count": 6,
"self": 0.6309961109986943
}
}
},
"_update_policy": {
"total": 1478.5605419400163,
"count": 1391,
"self": 864.5588314498668,
"children": {
"TorchPPOOptimizer.update": {
"total": 614.0017104901494,
"count": 68322,
"self": 614.0017104901494
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2580003385664895e-06,
"count": 1,
"self": 1.2580003385664895e-06
},
"TrainerController._save_models": {
"total": 0.1326419649994932,
"count": 1,
"self": 0.0021629069997288752,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13047905799976434,
"count": 1,
"self": 0.13047905799976434
}
}
}
}
}
}
}