Keldon-Lee's picture
First Push
2577ade verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8386714458465576,
"min": 0.8386714458465576,
"max": 2.829482316970825,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7970.7333984375,
"min": 7970.7333984375,
"max": 28883.35546875,
"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": 13.26478099822998,
"min": 0.3996841311454773,
"max": 13.26478099822998,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2586.63232421875,
"min": 77.5387191772461,
"max": 2679.775390625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06522922999426431,
"min": 0.06324809566622742,
"max": 0.07393546310195234,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26091691997705724,
"min": 0.2529923826649097,
"max": 0.3696773155097617,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1798370299751268,
"min": 0.15368611303582677,
"max": 0.2717487054712632,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7193481199005072,
"min": 0.6147444521433071,
"max": 1.358743527356316,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.347009730600001e-05,
"min": 1.347009730600001e-05,
"max": 0.00048647000270600005,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.388038922400004e-05,
"min": 5.388038922400004e-05,
"max": 0.00230860003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"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": 26.636363636363637,
"min": 4.431818181818182,
"max": 26.636363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1172.0,
"min": 195.0,
"max": 1433.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.636363636363637,
"min": 4.431818181818182,
"max": 26.636363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1172.0,
"min": 195.0,
"max": 1433.0,
"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": "1741355428",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741355852"
},
"total": 424.409925295,
"count": 1,
"self": 0.43156804099999135,
"children": {
"run_training.setup": {
"total": 0.022561597000049005,
"count": 1,
"self": 0.022561597000049005
},
"TrainerController.start_learning": {
"total": 423.95579565699995,
"count": 1,
"self": 0.3534029840029689,
"children": {
"TrainerController._reset_env": {
"total": 3.0107196849999127,
"count": 1,
"self": 3.0107196849999127
},
"TrainerController.advance": {
"total": 420.5064172369971,
"count": 18192,
"self": 0.3453684880041692,
"children": {
"env_step": {
"total": 298.9798139949953,
"count": 18192,
"self": 227.91258843504215,
"children": {
"SubprocessEnvManager._take_step": {
"total": 70.86107347097254,
"count": 18192,
"self": 1.2669063119949442,
"children": {
"TorchPolicy.evaluate": {
"total": 69.5941671589776,
"count": 18192,
"self": 69.5941671589776
}
}
},
"workers": {
"total": 0.2061520889806161,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 422.4982476920077,
"count": 18192,
"is_parallel": true,
"self": 222.15143786102362,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005495340000152282,
"count": 1,
"is_parallel": true,
"self": 0.0038781719999860798,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016171680001662025,
"count": 10,
"is_parallel": true,
"self": 0.0016171680001662025
}
}
},
"UnityEnvironment.step": {
"total": 0.034453295000048456,
"count": 1,
"is_parallel": true,
"self": 0.0006482190001406707,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036676099989563227,
"count": 1,
"is_parallel": true,
"self": 0.00036676099989563227
},
"communicator.exchange": {
"total": 0.031578650000028574,
"count": 1,
"is_parallel": true,
"self": 0.031578650000028574
},
"steps_from_proto": {
"total": 0.001859664999983579,
"count": 1,
"is_parallel": true,
"self": 0.0003530380006395717,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015066269993440073,
"count": 10,
"is_parallel": true,
"self": 0.0015066269993440073
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 200.34680983098406,
"count": 18191,
"is_parallel": true,
"self": 9.62914380898269,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.410234544006471,
"count": 18191,
"is_parallel": true,
"self": 5.410234544006471
},
"communicator.exchange": {
"total": 154.06577682199804,
"count": 18191,
"is_parallel": true,
"self": 154.06577682199804
},
"steps_from_proto": {
"total": 31.241654655996854,
"count": 18191,
"is_parallel": true,
"self": 5.589150437965145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.65250421803171,
"count": 181910,
"is_parallel": true,
"self": 25.65250421803171
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.18123475399761,
"count": 18192,
"self": 0.4267660730110947,
"children": {
"process_trajectory": {
"total": 26.955783327985955,
"count": 18192,
"self": 26.32261228398579,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6331710440001643,
"count": 4,
"self": 0.6331710440001643
}
}
},
"_update_policy": {
"total": 93.79868535300056,
"count": 90,
"self": 37.656419792007,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.142265560993565,
"count": 4587,
"self": 56.142265560993565
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.750000688451109e-07,
"count": 1,
"self": 8.750000688451109e-07
},
"TrainerController._save_models": {
"total": 0.08525487599990811,
"count": 1,
"self": 0.0009004399998957524,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08435443600001236,
"count": 1,
"self": 0.08435443600001236
}
}
}
}
}
}
}