sanak
First Push
0337094
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1682959645986557,
"min": 0.15867099165916443,
"max": 1.506880521774292,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 5011.1806640625,
"min": 4735.2265625,
"max": 45712.7265625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999874.0,
"min": 29952.0,
"max": 2999874.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999874.0,
"min": 29952.0,
"max": 2999874.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.7210549712181091,
"min": -0.10845237970352173,
"max": 0.7578170299530029,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 212.71121215820312,
"min": -26.13702392578125,
"max": 223.5560302734375,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.00986985769122839,
"min": -0.0024627591483294964,
"max": 0.3655122220516205,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 2.9116079807281494,
"min": -0.6230780482292175,
"max": 87.72293090820312,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06567495460123089,
"min": 0.06282450370079674,
"max": 0.0739719506367977,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9194493644172326,
"min": 0.4831191060146994,
"max": 1.0643952477354712,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.015629950854677842,
"min": 7.431710158474595e-05,
"max": 0.01817613847379107,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.2188193119654898,
"min": 0.0009661223206016972,
"max": 0.254465938633075,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5843994719000014e-06,
"min": 1.5843994719000014e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.218159260660002e-05,
"min": 2.218159260660002e-05,
"max": 0.0039691746769418,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.1005281,
"min": 0.1005281,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4073934,
"min": 1.3897045333333333,
"max": 2.7230581999999997,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.275719000000005e-05,
"min": 6.275719000000005e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008786006600000007,
"min": 0.0008786006600000007,
"max": 0.13231351418,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.006385217420756817,
"min": 0.006043681409209967,
"max": 0.51478111743927,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.08939304202795029,
"min": 0.08461154252290726,
"max": 3.6034677028656006,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 257.3333333333333,
"min": 240.4015748031496,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30108.0,
"min": 15984.0,
"max": 34119.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6913726324072251,
"min": -1.0000000521540642,
"max": 1.7446495598962164,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 197.89059799164534,
"min": -32.000001668930054,
"max": 217.84879883378744,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6913726324072251,
"min": -1.0000000521540642,
"max": 1.7446495598962164,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 197.89059799164534,
"min": -32.000001668930054,
"max": 217.84879883378744,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.016997803198549256,
"min": 0.016183584418554022,
"max": 11.107700765132904,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.988742974230263,
"min": 1.8125614548780504,
"max": 177.72321224212646,
"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": "1679525510",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"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": "1679532825"
},
"total": 7315.3184103389995,
"count": 1,
"self": 0.48973029399894585,
"children": {
"run_training.setup": {
"total": 0.18189264900001945,
"count": 1,
"self": 0.18189264900001945
},
"TrainerController.start_learning": {
"total": 7314.646787396,
"count": 1,
"self": 4.268599165970954,
"children": {
"TrainerController._reset_env": {
"total": 15.36947936799993,
"count": 1,
"self": 15.36947936799993
},
"TrainerController.advance": {
"total": 7294.916755728029,
"count": 193364,
"self": 4.459473178888402,
"children": {
"env_step": {
"total": 5194.265412260083,
"count": 193364,
"self": 4853.302222583042,
"children": {
"SubprocessEnvManager._take_step": {
"total": 338.484980422988,
"count": 193364,
"self": 14.76536371513805,
"children": {
"TorchPolicy.evaluate": {
"total": 323.7196167078499,
"count": 187562,
"self": 323.7196167078499
}
}
},
"workers": {
"total": 2.4782092540538088,
"count": 193364,
"self": 0.0,
"children": {
"worker_root": {
"total": 7300.44798310707,
"count": 193364,
"is_parallel": true,
"self": 2818.3921973280885,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00760889799994402,
"count": 1,
"is_parallel": true,
"self": 0.0057045399998969515,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019043580000470683,
"count": 8,
"is_parallel": true,
"self": 0.0019043580000470683
}
}
},
"UnityEnvironment.step": {
"total": 0.04411156599996957,
"count": 1,
"is_parallel": true,
"self": 0.0005082849997961603,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004787910000914053,
"count": 1,
"is_parallel": true,
"self": 0.0004787910000914053
},
"communicator.exchange": {
"total": 0.041487265999990086,
"count": 1,
"is_parallel": true,
"self": 0.041487265999990086
},
"steps_from_proto": {
"total": 0.0016372240000919192,
"count": 1,
"is_parallel": true,
"self": 0.00039222900011282036,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012449949999790988,
"count": 8,
"is_parallel": true,
"self": 0.0012449949999790988
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 4482.055785778982,
"count": 193363,
"is_parallel": true,
"self": 91.60308915026962,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 66.46697997091212,
"count": 193363,
"is_parallel": true,
"self": 66.46697997091212
},
"communicator.exchange": {
"total": 4052.0388550188986,
"count": 193363,
"is_parallel": true,
"self": 4052.0388550188986
},
"steps_from_proto": {
"total": 271.94686163890094,
"count": 193363,
"is_parallel": true,
"self": 57.69101242003933,
"children": {
"_process_rank_one_or_two_observation": {
"total": 214.2558492188616,
"count": 1546904,
"is_parallel": true,
"self": 214.2558492188616
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2096.191870289057,
"count": 193364,
"self": 8.328242416277135,
"children": {
"process_trajectory": {
"total": 393.51997354977243,
"count": 193364,
"self": 392.84927949577286,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6706940539995685,
"count": 6,
"self": 0.6706940539995685
}
}
},
"_update_policy": {
"total": 1694.3436543230073,
"count": 1390,
"self": 1090.6692263300206,
"children": {
"TorchPPOOptimizer.update": {
"total": 603.6744279929866,
"count": 68301,
"self": 603.6744279929866
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.819999154889956e-07,
"count": 1,
"self": 7.819999154889956e-07
},
"TrainerController._save_models": {
"total": 0.0919523520005896,
"count": 1,
"self": 0.0014702140006193076,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09048213799997029,
"count": 1,
"self": 0.09048213799997029
}
}
}
}
}
}
}