canyuzzz's picture
First training of SnowballTarget
ccaf19f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0683985948562622,
"min": 1.0505399703979492,
"max": 2.856743812561035,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10154.060546875,
"min": 10135.4482421875,
"max": 29161.640625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 11.100971221923828,
"min": 0.3159121572971344,
"max": 11.100971221923828,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2164.689453125,
"min": 61.28696060180664,
"max": 2232.4921875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06621256170848724,
"min": 0.06270043818655027,
"max": 0.07504260162283626,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.264850246833949,
"min": 0.26448789494838015,
"max": 0.36440214264302456,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19840646552688937,
"min": 0.12549643125042648,
"max": 0.29420505442163525,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7936258621075575,
"min": 0.5019857250017059,
"max": 1.3073527581551494,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.6940973060000016e-06,
"min": 2.6940973060000016e-06,
"max": 9.729400270600002e-05,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.0776389224000007e-05,
"min": 1.0776389224000007e-05,
"max": 0.00046172003828000015,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999998,
"min": 0.10269399999999998,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4107759999999999,
"min": 0.4107759999999999,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 22.40909090909091,
"min": 3.5454545454545454,
"max": 22.40909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 986.0,
"min": 156.0,
"max": 1216.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 22.40909090909091,
"min": 3.5454545454545454,
"max": 22.40909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 986.0,
"min": 156.0,
"max": 1216.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1750392009",
"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": "1750392688"
},
"total": 679.0561628589999,
"count": 1,
"self": 0.5921290739997858,
"children": {
"run_training.setup": {
"total": 0.04020085000001927,
"count": 1,
"self": 0.04020085000001927
},
"TrainerController.start_learning": {
"total": 678.4238329350001,
"count": 1,
"self": 0.6227447810056219,
"children": {
"TrainerController._reset_env": {
"total": 5.28716990199996,
"count": 1,
"self": 5.28716990199996
},
"TrainerController.advance": {
"total": 672.4354165139944,
"count": 18192,
"self": 0.6527347680221283,
"children": {
"env_step": {
"total": 405.4387772659984,
"count": 18192,
"self": 346.14850165999997,
"children": {
"SubprocessEnvManager._take_step": {
"total": 58.90022192898459,
"count": 18192,
"self": 2.2389166639839004,
"children": {
"TorchPolicy.evaluate": {
"total": 56.66130526500069,
"count": 18192,
"self": 56.66130526500069
}
}
},
"workers": {
"total": 0.39005367701383875,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 676.1516656840079,
"count": 18192,
"is_parallel": true,
"self": 377.56661200199846,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009047958999872208,
"count": 1,
"is_parallel": true,
"self": 0.006536595000170564,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0025113639997016435,
"count": 10,
"is_parallel": true,
"self": 0.0025113639997016435
}
}
},
"UnityEnvironment.step": {
"total": 0.06501586700005646,
"count": 1,
"is_parallel": true,
"self": 0.0007115379999049765,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046186400004444295,
"count": 1,
"is_parallel": true,
"self": 0.00046186400004444295
},
"communicator.exchange": {
"total": 0.06104141600008006,
"count": 1,
"is_parallel": true,
"self": 0.06104141600008006
},
"steps_from_proto": {
"total": 0.0028010490000269783,
"count": 1,
"is_parallel": true,
"self": 0.0004566989996419579,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023443500003850204,
"count": 10,
"is_parallel": true,
"self": 0.0023443500003850204
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 298.5850536820094,
"count": 18191,
"is_parallel": true,
"self": 13.872473838008545,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.765130337990968,
"count": 18191,
"is_parallel": true,
"self": 7.765130337990968
},
"communicator.exchange": {
"total": 234.63169397600814,
"count": 18191,
"is_parallel": true,
"self": 234.63169397600814
},
"steps_from_proto": {
"total": 42.31575553000175,
"count": 18191,
"is_parallel": true,
"self": 8.245369542002209,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.07038598799954,
"count": 181910,
"is_parallel": true,
"self": 34.07038598799954
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 266.34390447997384,
"count": 18192,
"self": 0.8605587459658182,
"children": {
"process_trajectory": {
"total": 33.22037922300888,
"count": 18192,
"self": 32.72023398600936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.500145236999515,
"count": 4,
"self": 0.500145236999515
}
}
},
"_update_policy": {
"total": 232.26296651099915,
"count": 90,
"self": 82.51287345898822,
"children": {
"TorchPPOOptimizer.update": {
"total": 149.75009305201093,
"count": 7645,
"self": 149.75009305201093
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1060001270379871e-06,
"count": 1,
"self": 1.1060001270379871e-06
},
"TrainerController._save_models": {
"total": 0.07850063199998658,
"count": 1,
"self": 0.0011046740000892896,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07739595799989729,
"count": 1,
"self": 0.07739595799989729
}
}
}
}
}
}
}