Petheron's picture
First Push
6b19ddd verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0794299840927124,
"min": 1.0794299840927124,
"max": 2.875368356704712,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 11018.8212890625,
"min": 9655.3623046875,
"max": 30743.78515625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499912.0,
"min": 9952.0,
"max": 499912.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 28.031293869018555,
"min": 0.1398555040359497,
"max": 28.031293869018555,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2831.16064453125,
"min": 13.565983772277832,
"max": 2874.48193359375,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.18867924528302,
"min": 2.9318181818181817,
"max": 28.18867924528302,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1494.0,
"min": 129.0,
"max": 1541.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.18867924528302,
"min": 2.9318181818181817,
"max": 28.18867924528302,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1494.0,
"min": 129.0,
"max": 1541.0,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.05033263741097471,
"min": 0.03943398371698362,
"max": 0.05565152114703618,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.10066527482194942,
"min": 0.07886796743396723,
"max": 0.16122617020151023,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.15460386209409027,
"min": 0.11456028199480736,
"max": 0.34142332721282453,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.30920772418818054,
"min": 0.22912056398961472,
"max": 0.9680693276664789,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0000990000000026e-06,
"min": 3.0000990000000026e-06,
"max": 0.00029604000132,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 6.000198000000005e-06,
"min": 6.000198000000005e-06,
"max": 0.0008366400211199997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10099999999999999,
"min": 0.10099999999999999,
"max": 0.19868000000000002,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.20199999999999999,
"min": 0.20199999999999999,
"max": 0.5788800000000001,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00010990000000000008,
"min": 0.00010990000000000008,
"max": 0.009868132,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00021980000000000017,
"min": 0.00021980000000000017,
"max": 0.027890112,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1775182270",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/opt/conda/envs/mlagents/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"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": "1775184002"
},
"total": 1731.2481412430006,
"count": 1,
"self": 0.9962522350006111,
"children": {
"run_training.setup": {
"total": 0.040671835000011924,
"count": 1,
"self": 0.040671835000011924
},
"TrainerController.start_learning": {
"total": 1730.211217173,
"count": 1,
"self": 1.4203198718478234,
"children": {
"TrainerController._reset_env": {
"total": 5.102338431999669,
"count": 1,
"self": 5.102338431999669
},
"TrainerController.advance": {
"total": 1723.511805726153,
"count": 45528,
"self": 1.507853168274778,
"children": {
"env_step": {
"total": 1005.7818981829059,
"count": 45528,
"self": 835.0904936537686,
"children": {
"SubprocessEnvManager._take_step": {
"total": 169.77223961616028,
"count": 45528,
"self": 4.765976292154846,
"children": {
"TorchPolicy.evaluate": {
"total": 165.00626332400543,
"count": 45528,
"self": 165.00626332400543
}
}
},
"workers": {
"total": 0.9191649129770667,
"count": 45528,
"self": 0.0,
"children": {
"worker_root": {
"total": 1723.664201627074,
"count": 45528,
"is_parallel": true,
"self": 1001.7793150400985,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008020751000003656,
"count": 1,
"is_parallel": true,
"self": 0.005416643999978987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002604107000024669,
"count": 10,
"is_parallel": true,
"self": 0.002604107000024669
}
}
},
"UnityEnvironment.step": {
"total": 0.044774385999971855,
"count": 1,
"is_parallel": true,
"self": 0.0007171639999796753,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044632999970417586,
"count": 1,
"is_parallel": true,
"self": 0.00044632999970417586
},
"communicator.exchange": {
"total": 0.04138005700042413,
"count": 1,
"is_parallel": true,
"self": 0.04138005700042413
},
"steps_from_proto": {
"total": 0.0022308349998638732,
"count": 1,
"is_parallel": true,
"self": 0.00043109999933221843,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017997350005316548,
"count": 10,
"is_parallel": true,
"self": 0.0017997350005316548
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 721.8848865869754,
"count": 45527,
"is_parallel": true,
"self": 34.15838527101096,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 18.018888696019076,
"count": 45527,
"is_parallel": true,
"self": 18.018888696019076
},
"communicator.exchange": {
"total": 556.0748600979896,
"count": 45527,
"is_parallel": true,
"self": 556.0748600979896
},
"steps_from_proto": {
"total": 113.63275252195581,
"count": 45527,
"is_parallel": true,
"self": 19.77222733788858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 93.86052518406723,
"count": 455270,
"is_parallel": true,
"self": 93.86052518406723
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 716.2220543749722,
"count": 45528,
"self": 1.9200498490422433,
"children": {
"process_trajectory": {
"total": 89.07567511193292,
"count": 45528,
"self": 87.13041705193245,
"children": {
"RLTrainer._checkpoint": {
"total": 1.9452580600004694,
"count": 10,
"self": 1.9452580600004694
}
}
},
"_update_policy": {
"total": 625.2263294139971,
"count": 113,
"self": 155.73877635694998,
"children": {
"TorchPPOOptimizer.update": {
"total": 469.4875530570471,
"count": 7684,
"self": 469.4875530570471
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3850003597326577e-06,
"count": 1,
"self": 1.3850003597326577e-06
},
"TrainerController._save_models": {
"total": 0.17675175799922727,
"count": 1,
"self": 0.01060500999847136,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1661467480007559,
"count": 1,
"self": 0.1661467480007559
}
}
}
}
}
}
}