ahforoughi's picture
First Push
b93f39b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0807324647903442,
"min": 1.0807324647903442,
"max": 2.8461053371429443,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10354.498046875,
"min": 10354.498046875,
"max": 29146.96484375,
"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": 12.872466087341309,
"min": 0.2798191010951996,
"max": 12.872466087341309,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2510.130859375,
"min": 54.28490447998047,
"max": 2598.914306640625,
"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.Losses.PolicyLoss.mean": {
"value": 0.06713295188013695,
"min": 0.06332136134105716,
"max": 0.07353326213356637,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2685318075205478,
"min": 0.25436817821316127,
"max": 0.36095829919855427,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18941276071264462,
"min": 0.11052791246295195,
"max": 0.28012132253132616,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7576510428505785,
"min": 0.4421116498518078,
"max": 1.4006066126566308,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"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.CumulativeReward.mean": {
"value": 25.25,
"min": 3.022727272727273,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1111.0,
"min": 133.0,
"max": 1392.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.25,
"min": 3.022727272727273,
"max": 25.30909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1111.0,
"min": 133.0,
"max": 1392.0,
"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": "1714068247",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714068668"
},
"total": 420.715021073,
"count": 1,
"self": 0.4777426770000375,
"children": {
"run_training.setup": {
"total": 0.04971012199996494,
"count": 1,
"self": 0.04971012199996494
},
"TrainerController.start_learning": {
"total": 420.187568274,
"count": 1,
"self": 0.5354431570043516,
"children": {
"TrainerController._reset_env": {
"total": 1.9202147020000666,
"count": 1,
"self": 1.9202147020000666
},
"TrainerController.advance": {
"total": 417.5849732109957,
"count": 18208,
"self": 0.24664360600365853,
"children": {
"env_step": {
"total": 417.33832960499205,
"count": 18208,
"self": 268.5468170329914,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.52372747999232,
"count": 18208,
"self": 1.3610523449710854,
"children": {
"TorchPolicy.evaluate": {
"total": 147.16267513502123,
"count": 18208,
"self": 147.16267513502123
}
}
},
"workers": {
"total": 0.2677850920083529,
"count": 18208,
"self": 0.0,
"children": {
"worker_root": {
"total": 419.10637281200604,
"count": 18208,
"is_parallel": true,
"self": 208.58721213401316,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022132899999860456,
"count": 1,
"is_parallel": true,
"self": 0.0005881309999722362,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016251590000138094,
"count": 10,
"is_parallel": true,
"self": 0.0016251590000138094
}
}
},
"UnityEnvironment.step": {
"total": 0.036491395999973975,
"count": 1,
"is_parallel": true,
"self": 0.0006436549999762065,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038819999997485866,
"count": 1,
"is_parallel": true,
"self": 0.00038819999997485866
},
"communicator.exchange": {
"total": 0.03356306400007725,
"count": 1,
"is_parallel": true,
"self": 0.03356306400007725
},
"steps_from_proto": {
"total": 0.001896476999945662,
"count": 1,
"is_parallel": true,
"self": 0.00037919599992619624,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015172810000194659,
"count": 10,
"is_parallel": true,
"self": 0.0015172810000194659
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.5191606779929,
"count": 18207,
"is_parallel": true,
"self": 10.005351809016133,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.179817442999479,
"count": 18207,
"is_parallel": true,
"self": 5.179817442999479
},
"communicator.exchange": {
"total": 163.3224772199834,
"count": 18207,
"is_parallel": true,
"self": 163.3224772199834
},
"steps_from_proto": {
"total": 32.011514205993876,
"count": 18207,
"is_parallel": true,
"self": 5.878366111971445,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.13314809402243,
"count": 182070,
"is_parallel": true,
"self": 26.13314809402243
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001329990000158432,
"count": 1,
"self": 0.0001329990000158432,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 412.45401418296944,
"count": 665045,
"is_parallel": true,
"self": 13.075854123977479,
"children": {
"process_trajectory": {
"total": 227.66651940699182,
"count": 665045,
"is_parallel": true,
"self": 227.00325328399163,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6632661230001986,
"count": 4,
"is_parallel": true,
"self": 0.6632661230001986
}
}
},
"_update_policy": {
"total": 171.71164065200014,
"count": 90,
"is_parallel": true,
"self": 50.22559865800213,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.48604199399801,
"count": 4587,
"is_parallel": true,
"self": 121.48604199399801
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14680420499985303,
"count": 1,
"self": 0.0016170659998806514,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14518713899997238,
"count": 1,
"self": 0.14518713899997238
}
}
}
}
}
}
}