Lew's picture
First Push
a853a13
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8766181468963623,
"min": 0.8766181468963623,
"max": 2.871908187866211,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8379.5927734375,
"min": 8379.5927734375,
"max": 29474.39453125,
"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": 12.966015815734863,
"min": 0.1805913895368576,
"max": 13.00028133392334,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2528.373046875,
"min": 35.03472900390625,
"max": 2652.057373046875,
"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": 0.07043736955515045,
"min": 0.0636912417720155,
"max": 0.07927823203527962,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2817494782206018,
"min": 0.254764967088062,
"max": 0.37382976997668815,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22113928403340136,
"min": 0.10471824084308143,
"max": 0.2817202842264783,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8845571361336054,
"min": 0.4188729633723257,
"max": 1.3812054217446084,
"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": 25.0,
"min": 2.977272727272727,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 131.0,
"max": 1405.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 2.977272727272727,
"max": 25.59090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 131.0,
"max": 1405.0,
"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": "1702018755",
"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",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1702019364"
},
"total": 609.125710299,
"count": 1,
"self": 0.5985058810001647,
"children": {
"run_training.setup": {
"total": 0.06333173999996689,
"count": 1,
"self": 0.06333173999996689
},
"TrainerController.start_learning": {
"total": 608.4638726779999,
"count": 1,
"self": 0.8982237799843915,
"children": {
"TrainerController._reset_env": {
"total": 2.7749932179999632,
"count": 1,
"self": 2.7749932179999632
},
"TrainerController.advance": {
"total": 604.6975548870153,
"count": 18201,
"self": 0.4415633460234858,
"children": {
"env_step": {
"total": 604.2559915409918,
"count": 18201,
"self": 471.40265742198727,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.40945637699633,
"count": 18201,
"self": 2.385483847998273,
"children": {
"TorchPolicy.evaluate": {
"total": 130.02397252899806,
"count": 18201,
"self": 130.02397252899806
}
}
},
"workers": {
"total": 0.4438777420081692,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 606.3017599149942,
"count": 18201,
"is_parallel": true,
"self": 282.77897908897984,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0059743520000097305,
"count": 1,
"is_parallel": true,
"self": 0.0043804030000274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015939489999823309,
"count": 10,
"is_parallel": true,
"self": 0.0015939489999823309
}
}
},
"UnityEnvironment.step": {
"total": 0.04304295899999033,
"count": 1,
"is_parallel": true,
"self": 0.0008148820000428714,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00046559700001580495,
"count": 1,
"is_parallel": true,
"self": 0.00046559700001580495
},
"communicator.exchange": {
"total": 0.03950345099997321,
"count": 1,
"is_parallel": true,
"self": 0.03950345099997321
},
"steps_from_proto": {
"total": 0.0022590289999584456,
"count": 1,
"is_parallel": true,
"self": 0.00046771299997772076,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017913159999807249,
"count": 10,
"is_parallel": true,
"self": 0.0017913159999807249
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 323.5227808260144,
"count": 18200,
"is_parallel": true,
"self": 14.547348780025914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.650367811994499,
"count": 18200,
"is_parallel": true,
"self": 7.650367811994499
},
"communicator.exchange": {
"total": 255.79094810799597,
"count": 18200,
"is_parallel": true,
"self": 255.79094810799597
},
"steps_from_proto": {
"total": 45.534116125998025,
"count": 18200,
"is_parallel": true,
"self": 8.999848288997327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.5342678370007,
"count": 182000,
"is_parallel": true,
"self": 36.5342678370007
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018923100014944794,
"count": 1,
"self": 0.00018923100014944794,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 599.2505218320118,
"count": 621345,
"is_parallel": true,
"self": 14.643019101038249,
"children": {
"process_trajectory": {
"total": 326.5536920079726,
"count": 621345,
"is_parallel": true,
"self": 325.6527815329724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9009104750001597,
"count": 4,
"is_parallel": true,
"self": 0.9009104750001597
}
}
},
"_update_policy": {
"total": 258.053810723001,
"count": 90,
"is_parallel": true,
"self": 75.11015662900309,
"children": {
"TorchPPOOptimizer.update": {
"total": 182.9436540939979,
"count": 4587,
"is_parallel": true,
"self": 182.9436540939979
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09291156200015394,
"count": 1,
"self": 0.0012758000000303582,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09163576200012358,
"count": 1,
"self": 0.09163576200012358
}
}
}
}
}
}
}