binhpham's picture
First Push
4d24725 verified
{
"name": "root",
"gauges": {
"Pyramids.Policy.Entropy.mean": {
"value": 0.3914129137992859,
"min": 0.3668580651283264,
"max": 1.498043179512024,
"count": 33
},
"Pyramids.Policy.Entropy.sum": {
"value": 11610.873046875,
"min": 11029.220703125,
"max": 45444.63671875,
"count": 33
},
"Pyramids.Step.mean": {
"value": 989990.0,
"min": 29952.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Step.sum": {
"value": 989990.0,
"min": 29952.0,
"max": 989990.0,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.mean": {
"value": 0.5770279169082642,
"min": -0.08904025703668594,
"max": 0.5770279169082642,
"count": 33
},
"Pyramids.Policy.ExtrinsicValueEstimate.sum": {
"value": 160.99078369140625,
"min": -21.280620574951172,
"max": 160.99078369140625,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.mean": {
"value": -0.017568960785865784,
"min": -0.017568960785865784,
"max": 0.32303211092948914,
"count": 33
},
"Pyramids.Policy.RndValueEstimate.sum": {
"value": -4.901740074157715,
"min": -4.901740074157715,
"max": 76.55860900878906,
"count": 33
},
"Pyramids.Losses.PolicyLoss.mean": {
"value": 0.06642365664343483,
"min": 0.06390482648308131,
"max": 0.0737026691859041,
"count": 33
},
"Pyramids.Losses.PolicyLoss.sum": {
"value": 0.9299311930080876,
"min": 0.5140947869723935,
"max": 1.0630745151760423,
"count": 33
},
"Pyramids.Losses.ValueLoss.mean": {
"value": 0.014164491160564856,
"min": 0.0002682115592286724,
"max": 0.016209013000579992,
"count": 33
},
"Pyramids.Losses.ValueLoss.sum": {
"value": 0.198302876247908,
"min": 0.0029503271515153966,
"max": 0.22692618200811987,
"count": 33
},
"Pyramids.Policy.LearningRate.mean": {
"value": 7.676261726992859e-06,
"min": 7.676261726992859e-06,
"max": 0.00029515063018788575,
"count": 33
},
"Pyramids.Policy.LearningRate.sum": {
"value": 0.00010746766417790002,
"min": 0.00010746766417790002,
"max": 0.003506729631090199,
"count": 33
},
"Pyramids.Policy.Epsilon.mean": {
"value": 0.10255872142857143,
"min": 0.10255872142857143,
"max": 0.19838354285714285,
"count": 33
},
"Pyramids.Policy.Epsilon.sum": {
"value": 1.4358221,
"min": 1.3886848,
"max": 2.5689098,
"count": 33
},
"Pyramids.Policy.Beta.mean": {
"value": 0.0002656162707142857,
"min": 0.0002656162707142857,
"max": 0.00983851593142857,
"count": 33
},
"Pyramids.Policy.Beta.sum": {
"value": 0.0037186277900000003,
"min": 0.0037186277900000003,
"max": 0.11691408901999999,
"count": 33
},
"Pyramids.Losses.RNDLoss.mean": {
"value": 0.011160486377775669,
"min": 0.011160486377775669,
"max": 0.37783390283584595,
"count": 33
},
"Pyramids.Losses.RNDLoss.sum": {
"value": 0.15624681115150452,
"min": 0.15624681115150452,
"max": 2.6448373794555664,
"count": 33
},
"Pyramids.Environment.EpisodeLength.mean": {
"value": 346.9111111111111,
"min": 346.9111111111111,
"max": 999.0,
"count": 33
},
"Pyramids.Environment.EpisodeLength.sum": {
"value": 31222.0,
"min": 16751.0,
"max": 32478.0,
"count": 33
},
"Pyramids.Environment.CumulativeReward.mean": {
"value": 1.5877033534009806,
"min": -0.999962551984936,
"max": 1.617185165024834,
"count": 33
},
"Pyramids.Environment.CumulativeReward.sum": {
"value": 141.30559845268726,
"min": -31.998801663517952,
"max": 141.30559845268726,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.mean": {
"value": 1.5877033534009806,
"min": -0.999962551984936,
"max": 1.617185165024834,
"count": 33
},
"Pyramids.Policy.ExtrinsicReward.sum": {
"value": 141.30559845268726,
"min": -31.998801663517952,
"max": 141.30559845268726,
"count": 33
},
"Pyramids.Policy.RndReward.mean": {
"value": 0.03948799187344959,
"min": 0.03948799187344959,
"max": 6.9646354133591934,
"count": 33
},
"Pyramids.Policy.RndReward.sum": {
"value": 3.514431276737014,
"min": 3.39339581184322,
"max": 118.39880202710629,
"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": "1743600591",
"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 Training --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743602872"
},
"total": 2281.164903774,
"count": 1,
"self": 0.7740005349996864,
"children": {
"run_training.setup": {
"total": 0.029768800000056217,
"count": 1,
"self": 0.029768800000056217
},
"TrainerController.start_learning": {
"total": 2280.361134439,
"count": 1,
"self": 1.5470909520104215,
"children": {
"TrainerController._reset_env": {
"total": 2.7733857159998934,
"count": 1,
"self": 2.7733857159998934
},
"TrainerController.advance": {
"total": 2275.90948939699,
"count": 63744,
"self": 1.5232869248902716,
"children": {
"env_step": {
"total": 1587.7294211270316,
"count": 63744,
"self": 1425.5644125050667,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.31482457997822,
"count": 63744,
"self": 4.9349335100043845,
"children": {
"TorchPolicy.evaluate": {
"total": 156.37989106997384,
"count": 62543,
"self": 156.37989106997384
}
}
},
"workers": {
"total": 0.8501840419867221,
"count": 63744,
"self": 0.0,
"children": {
"worker_root": {
"total": 2274.9696280859603,
"count": 63744,
"is_parallel": true,
"self": 967.2349679690253,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0025386810000327387,
"count": 1,
"is_parallel": true,
"self": 0.0007707320000918116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001767948999940927,
"count": 8,
"is_parallel": true,
"self": 0.001767948999940927
}
}
},
"UnityEnvironment.step": {
"total": 0.04781888899992737,
"count": 1,
"is_parallel": true,
"self": 0.0005729980000523938,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046215299994400993,
"count": 1,
"is_parallel": true,
"self": 0.00046215299994400993
},
"communicator.exchange": {
"total": 0.045114734999970096,
"count": 1,
"is_parallel": true,
"self": 0.045114734999970096
},
"steps_from_proto": {
"total": 0.0016690029999608669,
"count": 1,
"is_parallel": true,
"self": 0.0003713640001024032,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0012976389998584636,
"count": 8,
"is_parallel": true,
"self": 0.0012976389998584636
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1307.734660116935,
"count": 63743,
"is_parallel": true,
"self": 32.216679893939045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 23.149668198971767,
"count": 63743,
"is_parallel": true,
"self": 23.149668198971767
},
"communicator.exchange": {
"total": 1154.259862251022,
"count": 63743,
"is_parallel": true,
"self": 1154.259862251022
},
"steps_from_proto": {
"total": 98.10844977300212,
"count": 63743,
"is_parallel": true,
"self": 20.16364103689216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 77.94480873610996,
"count": 509944,
"is_parallel": true,
"self": 77.94480873610996
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 686.6567813450681,
"count": 63744,
"self": 2.7493348349992175,
"children": {
"process_trajectory": {
"total": 131.19839300606532,
"count": 63744,
"self": 130.88334272706538,
"children": {
"RLTrainer._checkpoint": {
"total": 0.31505027899993365,
"count": 2,
"self": 0.31505027899993365
}
}
},
"_update_policy": {
"total": 552.7090535040036,
"count": 450,
"self": 302.9028190100214,
"children": {
"TorchPPOOptimizer.update": {
"total": 249.80623449398217,
"count": 22800,
"self": 249.80623449398217
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0280000424245372e-06,
"count": 1,
"self": 1.0280000424245372e-06
},
"TrainerController._save_models": {
"total": 0.1311673459999838,
"count": 1,
"self": 0.0022106149999672198,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1289567310000166,
"count": 1,
"self": 0.1289567310000166
}
}
}
}
}
}
}