talebzeghmi's picture
Pyramids Training5 Memory
1db1ed4 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.36488646268844604,
"min": 0.3551276624202728,
"max": 0.7911593317985535,
"count": 134
},
"Pyramids.Policy.Entropy.sum": {
"value": 11104.224609375,
"min": 10301.54296875,
"max": 28915.892578125,
"count": 134
},
"Pyramids.Step.mean": {
"value": 5999934.0,
"min": 2009945.0,
"max": 5999934.0,
"count": 134
},
"Pyramids.Step.sum": {
"value": 5999934.0,
"min": 2009945.0,
"max": 5999934.0,
"count": 134
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.9218218922615051,
"min": 0.1252787560224533,
"max": 0.9716527462005615,
"count": 134
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 280.2338562011719,
"min": 10.022300720214844,
"max": 316.7587890625,
"count": 134
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.013818878680467606,
"min": -0.062205471098423004,
"max": 0.094496950507164,
"count": 134
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.200939178466797,
"min": -19.345901489257812,
"max": 27.7821044921875,
"count": 134
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 178.21052631578948,
"min": 136.0,
"max": 563.2083333333334,
"count": 134
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 27088.0,
"min": 680.0,
"max": 38451.0,
"count": 134
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.8210463471562657,
"min": 1.1867958924600057,
"max": 1.8639999955892563,
"count": 134
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 274.9779984205961,
"min": 9.319999977946281,
"max": 329.565797328949,
"count": 134
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.8210463471562657,
"min": 1.1867958924600057,
"max": 1.8639999955892563,
"count": 134
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 274.9779984205961,
"min": 9.319999977946281,
"max": 329.565797328949,
"count": 134
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01722965589627147,
"min": 0.0168254373341981,
"max": 0.21780517784467593,
"count": 134
},
"Pyramids.Policy.RndReward.sum": {
"value": 2.601678040336992,
"min": 0.3333440013229847,
"max": 14.053810398414498,
"count": 134
},
"Pyramids.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 134
},
"Pyramids.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 134
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.08789227641427715,
"min": 0.07172401092902873,
"max": 0.11426022358937189,
"count": 133
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.1757845528285543,
"min": 0.07172401092902873,
"max": 0.22366356179663854,
"count": 133
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012804161827079951,
"min": 0.003621110906897229,
"max": 0.016208569944137708,
"count": 133
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.025608323654159902,
"min": 0.003621110906897229,
"max": 0.03226217675255612,
"count": 133
},
"Pyramids.Policy.LearningRate.mean": {
"value": 5.52124815991656e-07,
"min": 5.52124815991656e-07,
"max": 0.00019897158367615004,
"count": 133
},
"Pyramids.Policy.LearningRate.sum": {
"value": 1.104249631983312e-06,
"min": 1.104249631983312e-06,
"max": 0.00039498136833956667,
"count": 133
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10018400833333334,
"min": 0.10018400833333334,
"max": 0.16632384999999997,
"count": 133
},
"Pyramids.Policy.Epsilon.sum": {
"value": 0.20036801666666668,
"min": 0.10121123333333334,
"max": 0.3316604333333333,
"count": 133
},
"Pyramids.Policy.Beta.mean": {
"value": 2.838243249999964e-05,
"min": 2.838243249999964e-05,
"max": 0.006635752615000002,
"count": 133
},
"Pyramids.Policy.Beta.sum": {
"value": 5.676486499999928e-05,
"min": 5.676486499999928e-05,
"max": 0.01317287729,
"count": 133
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.008040777407586575,
"min": 0.008006304502487183,
"max": 0.041542429476976395,
"count": 133
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.01608155481517315,
"min": 0.008109976537525654,
"max": 0.07683394849300385,
"count": 133
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1772391963",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training5 Memory --no-graphics --num-envs=10 --resume",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1772395571"
},
"total": 3607.5321902899996,
"count": 1,
"self": 0.5754533569997875,
"children": {
"run_training.setup": {
"total": 0.12450850899949728,
"count": 1,
"self": 0.12450850899949728
},
"TrainerController.start_learning": {
"total": 3606.8322284240003,
"count": 1,
"self": 3.0190472318681714,
"children": {
"TrainerController._reset_env": {
"total": 2.603950913000517,
"count": 1,
"self": 2.603950913000517
},
"TrainerController.advance": {
"total": 3601.0312512971304,
"count": 59227,
"self": 2.1109578761934245,
"children": {
"env_step": {
"total": 1449.3035915528708,
"count": 59227,
"self": 455.9942536251092,
"children": {
"SubprocessEnvManager._take_step": {
"total": 990.0442914250762,
"count": 264306,
"self": 34.1138892994295,
"children": {
"TorchPolicy.evaluate": {
"total": 955.9304021256467,
"count": 250585,
"self": 955.9304021256467
}
}
},
"workers": {
"total": 3.2650465026854363,
"count": 59227,
"self": 0.0,
"children": {
"worker_root": {
"total": 36046.44138467785,
"count": 264302,
"is_parallel": true,
"self": 28862.25714012814,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.02023548000215669,
"count": 10,
"is_parallel": true,
"self": 0.006409738003640086,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.013825741998516605,
"count": 80,
"is_parallel": true,
"self": 0.013825741998516605
}
}
},
"UnityEnvironment.step": {
"total": 0.5743121019986575,
"count": 10,
"is_parallel": true,
"self": 0.00606169700040482,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.003629601998909493,
"count": 10,
"is_parallel": true,
"self": 0.003629601998909493
},
"communicator.exchange": {
"total": 0.5479624359977606,
"count": 10,
"is_parallel": true,
"self": 0.5479624359977606
},
"steps_from_proto": {
"total": 0.01665836700158252,
"count": 10,
"is_parallel": true,
"self": 0.004257175998645835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.012401191002936685,
"count": 80,
"is_parallel": true,
"self": 0.012401191002936685
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 7184.18424454971,
"count": 264292,
"is_parallel": true,
"self": 139.60044607177042,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 90.55896083296466,
"count": 264292,
"is_parallel": true,
"self": 90.55896083296466
},
"communicator.exchange": {
"total": 6564.569057943758,
"count": 264292,
"is_parallel": true,
"self": 6564.569057943758
},
"steps_from_proto": {
"total": 389.45577970121667,
"count": 264292,
"is_parallel": true,
"self": 82.57030775551902,
"children": {
"_process_rank_one_or_two_observation": {
"total": 306.88547194569765,
"count": 2114336,
"is_parallel": true,
"self": 306.88547194569765
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 2149.6167018680662,
"count": 59227,
"self": 8.618607001981218,
"children": {
"process_trajectory": {
"total": 932.7226188410896,
"count": 59227,
"self": 926.6471830700939,
"children": {
"RLTrainer._checkpoint": {
"total": 6.075435770995682,
"count": 34,
"self": 6.075435770995682
}
}
},
"_update_policy": {
"total": 1208.2754760249954,
"count": 220,
"self": 669.2232708559295,
"children": {
"TorchPPOOptimizer.update": {
"total": 539.0522051690659,
"count": 17600,
"self": 539.0522051690659
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2140008038841188e-06,
"count": 1,
"self": 1.2140008038841188e-06
},
"TrainerController._save_models": {
"total": 0.17797776800034626,
"count": 1,
"self": 0.0029449619996739784,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17503280600067228,
"count": 1,
"self": 0.17503280600067228
}
}
}
}
}
}
}