LoicSteve's picture
First Push
9908c3b
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9350971579551697,
"min": 0.9235278367996216,
"max": 2.869410276412964,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8938.59375,
"min": 8938.59375,
"max": 29480.3203125,
"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": 12.753621101379395,
"min": 0.35487866401672363,
"max": 12.753621101379395,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2486.9560546875,
"min": 68.8464584350586,
"max": 2583.812744140625,
"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": 0.06775942715210154,
"min": 0.05889173090904745,
"max": 0.07254601501809507,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27103770860840615,
"min": 0.2355669236361898,
"max": 0.36273007509047533,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19403310730030723,
"min": 0.13014037480609783,
"max": 0.27568888503546807,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7761324292012289,
"min": 0.5205614992243913,
"max": 1.2801945685755973,
"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": 24.772727272727273,
"min": 3.4545454545454546,
"max": 25.509090909090908,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1090.0,
"min": 152.0,
"max": 1403.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.772727272727273,
"min": 3.4545454545454546,
"max": 25.509090909090908,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1090.0,
"min": 152.0,
"max": 1403.0,
"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": "1704250157",
"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": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1704250756"
},
"total": 598.381784448,
"count": 1,
"self": 0.5991539139999986,
"children": {
"run_training.setup": {
"total": 0.09691960899999685,
"count": 1,
"self": 0.09691960899999685
},
"TrainerController.start_learning": {
"total": 597.685710925,
"count": 1,
"self": 0.8390813300026139,
"children": {
"TrainerController._reset_env": {
"total": 4.12113145699999,
"count": 1,
"self": 4.12113145699999
},
"TrainerController.advance": {
"total": 592.6171713849974,
"count": 18201,
"self": 0.4309419440090778,
"children": {
"env_step": {
"total": 592.1862294409883,
"count": 18201,
"self": 457.6859170589959,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.0794980380016,
"count": 18201,
"self": 2.2743473409969397,
"children": {
"TorchPolicy.evaluate": {
"total": 131.80515069700465,
"count": 18201,
"self": 131.80515069700465
}
}
},
"workers": {
"total": 0.42081434399079853,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 595.7584139320093,
"count": 18201,
"is_parallel": true,
"self": 274.1412656130169,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006152956999983417,
"count": 1,
"is_parallel": true,
"self": 0.003942495999865514,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022104610001179026,
"count": 10,
"is_parallel": true,
"self": 0.0022104610001179026
}
}
},
"UnityEnvironment.step": {
"total": 0.04384782099998574,
"count": 1,
"is_parallel": true,
"self": 0.0009005539998838685,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004536570000368556,
"count": 1,
"is_parallel": true,
"self": 0.0004536570000368556
},
"communicator.exchange": {
"total": 0.039914744000043356,
"count": 1,
"is_parallel": true,
"self": 0.039914744000043356
},
"steps_from_proto": {
"total": 0.0025788660000216623,
"count": 1,
"is_parallel": true,
"self": 0.0006496020001236502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019292639998980121,
"count": 10,
"is_parallel": true,
"self": 0.0019292639998980121
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 321.61714831899235,
"count": 18200,
"is_parallel": true,
"self": 15.488880284994423,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.947645072997602,
"count": 18200,
"is_parallel": true,
"self": 7.947645072997602
},
"communicator.exchange": {
"total": 252.57457834500565,
"count": 18200,
"is_parallel": true,
"self": 252.57457834500565
},
"steps_from_proto": {
"total": 45.606044615994676,
"count": 18200,
"is_parallel": true,
"self": 8.819186388956837,
"children": {
"_process_rank_one_or_two_observation": {
"total": 36.78685822703784,
"count": 182000,
"is_parallel": true,
"self": 36.78685822703784
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017303399999946123,
"count": 1,
"self": 0.00017303399999946123,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 585.101747549989,
"count": 809015,
"is_parallel": true,
"self": 18.812563703945216,
"children": {
"process_trajectory": {
"total": 314.5817787100439,
"count": 809015,
"is_parallel": true,
"self": 314.0317807360439,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5499979740000072,
"count": 4,
"is_parallel": true,
"self": 0.5499979740000072
}
}
},
"_update_policy": {
"total": 251.70740513599986,
"count": 90,
"is_parallel": true,
"self": 72.97334771300228,
"children": {
"TorchPPOOptimizer.update": {
"total": 178.73405742299758,
"count": 4587,
"is_parallel": true,
"self": 178.73405742299758
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10815371899991533,
"count": 1,
"self": 0.009663941999974668,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09848977699994066,
"count": 1,
"self": 0.09848977699994066
}
}
}
}
}
}
}