gnieto's picture
First Push
d0e0383
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.1393812596797943,
"min": 0.1393812596797943,
"max": 1.4600805044174194,
"count": 100
},
"Pyramids.Policy.Entropy.sum": {
"value": 4163.59716796875,
"min": 4163.59716796875,
"max": 44293.00390625,
"count": 100
},
"Pyramids.Step.mean": {
"value": 2999941.0,
"min": 29952.0,
"max": 2999941.0,
"count": 100
},
"Pyramids.Step.sum": {
"value": 2999941.0,
"min": 29952.0,
"max": 2999941.0,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.693597674369812,
"min": -0.1745767444372177,
"max": 0.8314973711967468,
"count": 100
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 200.44972229003906,
"min": -41.37468719482422,
"max": 245.29171752929688,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": 0.01610846258699894,
"min": -0.02259635180234909,
"max": 0.36757901310920715,
"count": 100
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": 4.655345916748047,
"min": -6.259189605712891,
"max": 87.11622619628906,
"count": 100
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.0703070365762826,
"min": 0.06417649519976712,
"max": 0.07567170739933037,
"count": 100
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9842985120679564,
"min": 0.4688840791460624,
"max": 1.0637842909588167,
"count": 100
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.012899709565057751,
"min": 3.441421429449427e-05,
"max": 0.016918947943070504,
"count": 100
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.18059593391080853,
"min": 0.0004473847858284255,
"max": 0.2422274477390673,
"count": 100
},
"Pyramids.Policy.LearningRate.mean": {
"value": 1.5663780493357156e-06,
"min": 1.5663780493357156e-06,
"max": 0.00029838354339596195,
"count": 100
},
"Pyramids.Policy.LearningRate.sum": {
"value": 2.192929269070002e-05,
"min": 2.192929269070002e-05,
"max": 0.003529971023343033,
"count": 100
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10052209285714286,
"min": 0.10052209285714286,
"max": 0.19946118095238097,
"count": 100
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4073093,
"min": 1.3897045333333333,
"max": 2.5875566666666674,
"count": 100
},
"Pyramids.Policy.Beta.mean": {
"value": 6.215707642857149e-05,
"min": 6.215707642857149e-05,
"max": 0.009946171977142856,
"count": 100
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0008701990700000008,
"min": 0.0008701990700000008,
"max": 0.11767803097000001,
"count": 100
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.005558049771934748,
"min": 0.005558049771934748,
"max": 0.31444793939590454,
"count": 100
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.07781269401311874,
"min": 0.07781269401311874,
"max": 2.2011356353759766,
"count": 100
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 260.9051724137931,
"min": 213.55725190839695,
"max": 999.0,
"count": 100
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 30265.0,
"min": 15984.0,
"max": 32775.0,
"count": 100
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.6701172274248353,
"min": -1.0000000521540642,
"max": 1.7701666471971707,
"count": 100
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 193.7335983812809,
"min": -32.000001668930054,
"max": 233.66199743002653,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.6701172274248353,
"min": -1.0000000521540642,
"max": 1.7701666471971707,
"count": 100
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 193.7335983812809,
"min": -32.000001668930054,
"max": 233.66199743002653,
"count": 100
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.01529131840878359,
"min": 0.01418612290280945,
"max": 6.1272799000144005,
"count": 100
},
"Pyramids.Policy.RndReward.sum": {
"value": 1.7737929354188964,
"min": 1.691239808431419,
"max": 98.03647840023041,
"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": "1674668397",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674674986"
},
"total": 6588.625298175,
"count": 1,
"self": 0.47532884200063563,
"children": {
"run_training.setup": {
"total": 0.10772796400033258,
"count": 1,
"self": 0.10772796400033258
},
"TrainerController.start_learning": {
"total": 6588.042241368999,
"count": 1,
"self": 3.995755237981939,
"children": {
"TrainerController._reset_env": {
"total": 6.134869720999632,
"count": 1,
"self": 6.134869720999632
},
"TrainerController.advance": {
"total": 6577.826070638017,
"count": 193087,
"self": 3.968513090855595,
"children": {
"env_step": {
"total": 4578.043302063129,
"count": 193087,
"self": 4249.517733832559,
"children": {
"SubprocessEnvManager._take_step": {
"total": 326.03503741640316,
"count": 193087,
"self": 13.628242801607485,
"children": {
"TorchPolicy.evaluate": {
"total": 312.4067946147957,
"count": 187557,
"self": 105.13227492770056,
"children": {
"TorchPolicy.sample_actions": {
"total": 207.2745196870951,
"count": 187557,
"self": 207.2745196870951
}
}
}
}
},
"workers": {
"total": 2.4905308141665046,
"count": 193087,
"self": 0.0,
"children": {
"worker_root": {
"total": 6574.296670590558,
"count": 193087,
"is_parallel": true,
"self": 2635.617659478471,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0018349060001128237,
"count": 1,
"is_parallel": true,
"self": 0.000691457999892009,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011434480002208147,
"count": 8,
"is_parallel": true,
"self": 0.0011434480002208147
}
}
},
"UnityEnvironment.step": {
"total": 0.04963875299972642,
"count": 1,
"is_parallel": true,
"self": 0.000499378999847977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005663980000463198,
"count": 1,
"is_parallel": true,
"self": 0.0005663980000463198
},
"communicator.exchange": {
"total": 0.04684669199968994,
"count": 1,
"is_parallel": true,
"self": 0.04684669199968994
},
"steps_from_proto": {
"total": 0.0017262840001421864,
"count": 1,
"is_parallel": true,
"self": 0.0004422510000949842,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012840330000472022,
"count": 8,
"is_parallel": true,
"self": 0.0012840330000472022
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3938.679011112087,
"count": 193086,
"is_parallel": true,
"self": 83.87159939221556,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 71.88812484226855,
"count": 193086,
"is_parallel": true,
"self": 71.88812484226855
},
"communicator.exchange": {
"total": 3490.8649132919904,
"count": 193086,
"is_parallel": true,
"self": 3490.8649132919904
},
"steps_from_proto": {
"total": 292.05437358561267,
"count": 193086,
"is_parallel": true,
"self": 69.5771471440521,
"children": {
"_process_rank_one_or_two_observation": {
"total": 222.47722644156056,
"count": 1544688,
"is_parallel": true,
"self": 222.47722644156056
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1995.8142554840324,
"count": 193087,
"self": 7.263999075844822,
"children": {
"process_trajectory": {
"total": 462.76671225617247,
"count": 193087,
"self": 462.2310994921718,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5356127640006889,
"count": 6,
"self": 0.5356127640006889
}
}
},
"_update_policy": {
"total": 1525.783544152015,
"count": 1366,
"self": 570.3343731689529,
"children": {
"TorchPPOOptimizer.update": {
"total": 955.4491709830622,
"count": 68397,
"self": 955.4491709830622
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1190004443051293e-06,
"count": 1,
"self": 1.1190004443051293e-06
},
"TrainerController._save_models": {
"total": 0.08554465300039737,
"count": 1,
"self": 0.001361955000902526,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08418269799949485,
"count": 1,
"self": 0.08418269799949485
}
}
}
}
}
}
}