whyguu's picture
ppo pyramidsRND
e34578b verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.4608817398548126,
"min": 0.45601212978363037,
"max": 1.423614263534546,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 13826.4521484375,
"min": 13651.1787109375,
"max": 43186.76171875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989938.0,
"min": 29952.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989938.0,
"min": 29952.0,
"max": 989938.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.4780595302581787,
"min": -0.11348436772823334,
"max": 0.5172157883644104,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 131.46636962890625,
"min": -27.46321678161621,
"max": 142.75155639648438,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.025942226871848106,
"min": -0.025942226871848106,
"max": 0.32661837339401245,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -7.134112358093262,
"min": -7.134112358093262,
"max": 78.38841247558594,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06831391085381423,
"min": 0.06619875052814787,
"max": 0.07333131036686115,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9563947519533993,
"min": 0.490403915746753,
"max": 1.046465949562844,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.016928106448044076,
"min": 0.000980977337410583,
"max": 0.017745495939120053,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.23699349027261704,
"min": 0.00893554979221262,
"max": 0.24843694314768072,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.682797439100005e-06,
"min": 7.682797439100005e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010755916414740008,
"min": 0.00010755916414740008,
"max": 0.0036345931884689997,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10256089999999998,
"min": 0.10256089999999998,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358525999999998,
"min": 1.3691136000000002,
"max": 2.6115310000000003,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002658339100000002,
"min": 0.0002658339100000002,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.003721674740000003,
"min": 0.003721674740000003,
"max": 0.1211719469,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.007107212208211422,
"min": 0.007107212208211422,
"max": 0.5102056264877319,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.09950096905231476,
"min": 0.09950096905231476,
"max": 3.571439504623413,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 392.0617283950617,
"min": 355.7808219178082,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31757.0,
"min": 15984.0,
"max": 32111.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.45974318480786,
"min": -1.0000000521540642,
"max": 1.562005456792165,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 118.23919796943665,
"min": -32.000001668930054,
"max": 124.34539856761694,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.45974318480786,
"min": -1.0000000521540642,
"max": 1.562005456792165,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 118.23919796943665,
"min": -32.000001668930054,
"max": 124.34539856761694,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.02802692733692109,
"min": 0.02802692733692109,
"max": 11.250846760347486,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.270181114290608,
"min": 2.074485746008577,
"max": 180.01354816555977,
"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": "1712028279",
"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": "1712030399"
},
"total": 2120.64303439,
"count": 1,
"self": 0.4762116910005716,
"children": {
"run_training.setup": {
"total": 0.08211306899988813,
"count": 1,
"self": 0.08211306899988813
},
"TrainerController.start_learning": {
"total": 2120.08470963,
"count": 1,
"self": 1.219195686000603,
"children": {
"TrainerController._reset_env": {
"total": 2.2936385339999106,
"count": 1,
"self": 2.2936385339999106
},
"TrainerController.advance": {
"total": 2116.4883411469996,
"count": 63778,
"self": 1.392160533906008,
"children": {
"env_step": {
"total": 1516.380489454067,
"count": 63778,
"self": 1393.266622263042,
"children": {
"SubprocessEnvManager._take_step": {
"total": 122.36404871198101,
"count": 63778,
"self": 4.389889352018145,
"children": {
"TorchPolicy.evaluate": {
"total": 117.97415935996287,
"count": 62553,
"self": 117.97415935996287
}
}
},
"workers": {
"total": 0.7498184790438245,
"count": 63778,
"self": 0.0,
"children": {
"worker_root": {
"total": 2115.302903787985,
"count": 63778,
"is_parallel": true,
"self": 834.4426389549326,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024134459999913815,
"count": 1,
"is_parallel": true,
"self": 0.0006748579999111826,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001738588000080199,
"count": 8,
"is_parallel": true,
"self": 0.001738588000080199
}
}
},
"UnityEnvironment.step": {
"total": 0.04640474699999686,
"count": 1,
"is_parallel": true,
"self": 0.0006129429998509295,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004552280001917097,
"count": 1,
"is_parallel": true,
"self": 0.0004552280001917097
},
"communicator.exchange": {
"total": 0.043723783999894295,
"count": 1,
"is_parallel": true,
"self": 0.043723783999894295
},
"steps_from_proto": {
"total": 0.001612792000059926,
"count": 1,
"is_parallel": true,
"self": 0.00035955500015916186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012532369999007642,
"count": 8,
"is_parallel": true,
"self": 0.0012532369999007642
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1280.8602648330525,
"count": 63777,
"is_parallel": true,
"self": 32.87929669596542,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 22.295127030001595,
"count": 63777,
"is_parallel": true,
"self": 22.295127030001595
},
"communicator.exchange": {
"total": 1131.3787755210142,
"count": 63777,
"is_parallel": true,
"self": 1131.3787755210142
},
"steps_from_proto": {
"total": 94.3070655860713,
"count": 63777,
"is_parallel": true,
"self": 18.43647819920625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 75.87058738686505,
"count": 510216,
"is_parallel": true,
"self": 75.87058738686505
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 598.7156911590264,
"count": 63778,
"self": 2.430362326005934,
"children": {
"process_trajectory": {
"total": 120.79306248101898,
"count": 63778,
"self": 120.60189507001883,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19116741100015133,
"count": 2,
"self": 0.19116741100015133
}
}
},
"_update_policy": {
"total": 475.4922663520015,
"count": 449,
"self": 277.50283131598303,
"children": {
"TorchPPOOptimizer.update": {
"total": 197.98943503601845,
"count": 22800,
"self": 197.98943503601845
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.000000318337698e-07,
"count": 1,
"self": 9.000000318337698e-07
},
"TrainerController._save_models": {
"total": 0.08353336299978764,
"count": 1,
"self": 0.0013295259996084496,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08220383700017919,
"count": 1,
"self": 0.08220383700017919
}
}
}
}
}
}
}