cashmerepancake's picture
First Push
22d03cf verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.2364305257797241,
"min": 1.2364305257797241,
"max": 2.84671688079834,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 12730.2890625,
"min": 12730.2890625,
"max": 29059.28515625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 9.770759582519531,
"min": 0.39459770917892456,
"max": 9.770759582519531,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1993.23486328125,
"min": 76.55195617675781,
"max": 1993.23486328125,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06454319748685093,
"min": 0.06395584781592548,
"max": 0.07290951257791853,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.32271598743425467,
"min": 0.2558233912637019,
"max": 0.35455904554178497,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2317571495093551,
"min": 0.1197664838377843,
"max": 0.2790476361910502,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.1587857475467755,
"min": 0.4790659353511372,
"max": 1.395238180955251,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 20.345454545454544,
"min": 3.3181818181818183,
"max": 20.345454545454544,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 146.0,
"max": 1119.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 20.345454545454544,
"min": 3.3181818181818183,
"max": 20.345454545454544,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 146.0,
"max": 1119.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1749702885",
"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/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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1749703156"
},
"total": 271.13283035999996,
"count": 1,
"self": 0.5440474419999646,
"children": {
"run_training.setup": {
"total": 0.02827851200004261,
"count": 1,
"self": 0.02827851200004261
},
"TrainerController.start_learning": {
"total": 270.56050440599995,
"count": 1,
"self": 0.3004841030077614,
"children": {
"TrainerController._reset_env": {
"total": 3.416117196000073,
"count": 1,
"self": 3.416117196000073
},
"TrainerController.advance": {
"total": 266.7700163669921,
"count": 9128,
"self": 0.30933764500218786,
"children": {
"env_step": {
"total": 186.11167169100065,
"count": 9128,
"self": 158.25194716101532,
"children": {
"SubprocessEnvManager._take_step": {
"total": 27.686176809994663,
"count": 9128,
"self": 0.9046744630055628,
"children": {
"TorchPolicy.evaluate": {
"total": 26.7815023469891,
"count": 9128,
"self": 26.7815023469891
}
}
},
"workers": {
"total": 0.17354771999066543,
"count": 9128,
"self": 0.0,
"children": {
"worker_root": {
"total": 269.56519340500563,
"count": 9128,
"is_parallel": true,
"self": 132.15326019601207,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006407199000022956,
"count": 1,
"is_parallel": true,
"self": 0.004624928999987787,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017822700000351688,
"count": 10,
"is_parallel": true,
"self": 0.0017822700000351688
}
}
},
"UnityEnvironment.step": {
"total": 0.04223566899997877,
"count": 1,
"is_parallel": true,
"self": 0.000789441999927476,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000585406000027433,
"count": 1,
"is_parallel": true,
"self": 0.000585406000027433
},
"communicator.exchange": {
"total": 0.03839771800005565,
"count": 1,
"is_parallel": true,
"self": 0.03839771800005565
},
"steps_from_proto": {
"total": 0.002463102999968214,
"count": 1,
"is_parallel": true,
"self": 0.00047153700006674626,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001991565999901468,
"count": 10,
"is_parallel": true,
"self": 0.001991565999901468
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 137.41193320899356,
"count": 9127,
"is_parallel": true,
"self": 6.72129588500286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.5186906869984114,
"count": 9127,
"is_parallel": true,
"self": 3.5186906869984114
},
"communicator.exchange": {
"total": 107.1119511669998,
"count": 9127,
"is_parallel": true,
"self": 107.1119511669998
},
"steps_from_proto": {
"total": 20.059995469992487,
"count": 9127,
"is_parallel": true,
"self": 3.7666657149889033,
"children": {
"_process_rank_one_or_two_observation": {
"total": 16.293329755003583,
"count": 91270,
"is_parallel": true,
"self": 16.293329755003583
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 80.34900703098924,
"count": 9128,
"self": 0.35493839797504734,
"children": {
"process_trajectory": {
"total": 14.78821887101401,
"count": 9128,
"self": 14.544118792013819,
"children": {
"RLTrainer._checkpoint": {
"total": 0.24410007900019082,
"count": 2,
"self": 0.24410007900019082
}
}
},
"_update_policy": {
"total": 65.20584976200018,
"count": 45,
"self": 23.94346632900283,
"children": {
"TorchPPOOptimizer.update": {
"total": 41.26238343299735,
"count": 2292,
"self": 41.26238343299735
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2900000001536682e-06,
"count": 1,
"self": 1.2900000001536682e-06
},
"TrainerController._save_models": {
"total": 0.07388545000003433,
"count": 1,
"self": 0.0010449510000398732,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07284049899999445,
"count": 1,
"self": 0.07284049899999445
}
}
}
}
}
}
}