wuwx's picture
First Push
b174c22
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9303784370422363,
"min": 0.9066445827484131,
"max": 2.857640504837036,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8893.4873046875,
"min": 8893.4873046875,
"max": 29485.134765625,
"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": 12.850105285644531,
"min": 0.4931575357913971,
"max": 12.850105285644531,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2505.7705078125,
"min": 95.67256164550781,
"max": 2595.42578125,
"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": 0.06955032421398095,
"min": 0.06543388322081906,
"max": 0.07299271764235991,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2782012968559238,
"min": 0.2711648469227001,
"max": 0.3649635882117996,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2068518407496751,
"min": 0.14613490530595585,
"max": 0.2818346202373504,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8274073629987004,
"min": 0.5845396212238234,
"max": 1.409173101186752,
"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": 25.681818181818183,
"min": 4.136363636363637,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1130.0,
"min": 182.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.681818181818183,
"min": 4.136363636363637,
"max": 25.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1130.0,
"min": 182.0,
"max": 1396.0,
"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": "1702902800",
"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": "1702903250"
},
"total": 449.976774869,
"count": 1,
"self": 0.4446721549999211,
"children": {
"run_training.setup": {
"total": 0.07683380000003126,
"count": 1,
"self": 0.07683380000003126
},
"TrainerController.start_learning": {
"total": 449.45526891400004,
"count": 1,
"self": 0.5821147840256344,
"children": {
"TrainerController._reset_env": {
"total": 3.094831189000047,
"count": 1,
"self": 3.094831189000047
},
"TrainerController.advance": {
"total": 445.69118382597446,
"count": 18200,
"self": 0.2821841529548692,
"children": {
"env_step": {
"total": 445.4089996730196,
"count": 18200,
"self": 293.52247369004033,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.60469203297987,
"count": 18200,
"self": 1.4879622029696975,
"children": {
"TorchPolicy.evaluate": {
"total": 150.11672983001017,
"count": 18200,
"self": 150.11672983001017
}
}
},
"workers": {
"total": 0.2818339499993954,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.2716238690101,
"count": 18200,
"is_parallel": true,
"self": 219.39226005001262,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005537489999937861,
"count": 1,
"is_parallel": true,
"self": 0.00408282700016116,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014546629997767013,
"count": 10,
"is_parallel": true,
"self": 0.0014546629997767013
}
}
},
"UnityEnvironment.step": {
"total": 0.051119765000066764,
"count": 1,
"is_parallel": true,
"self": 0.0010794890000624946,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041558899999927235,
"count": 1,
"is_parallel": true,
"self": 0.00041558899999927235
},
"communicator.exchange": {
"total": 0.047524065000061455,
"count": 1,
"is_parallel": true,
"self": 0.047524065000061455
},
"steps_from_proto": {
"total": 0.0021006219999435416,
"count": 1,
"is_parallel": true,
"self": 0.00039028000014695863,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001710341999796583,
"count": 10,
"is_parallel": true,
"self": 0.001710341999796583
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.8793638189975,
"count": 18199,
"is_parallel": true,
"self": 10.683156814994732,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.520318803999089,
"count": 18199,
"is_parallel": true,
"self": 5.520318803999089
},
"communicator.exchange": {
"total": 178.7288429149836,
"count": 18199,
"is_parallel": true,
"self": 178.7288429149836
},
"steps_from_proto": {
"total": 33.94704528502007,
"count": 18199,
"is_parallel": true,
"self": 6.37409569003546,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.572949594984607,
"count": 181990,
"is_parallel": true,
"self": 27.572949594984607
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012058299989803345,
"count": 1,
"self": 0.00012058299989803345,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 440.4084816250063,
"count": 645953,
"is_parallel": true,
"self": 13.704881433899345,
"children": {
"process_trajectory": {
"total": 245.32308923910693,
"count": 645953,
"is_parallel": true,
"self": 244.85805575710697,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4650334819999671,
"count": 4,
"is_parallel": true,
"self": 0.4650334819999671
}
}
},
"_update_policy": {
"total": 181.380510952,
"count": 90,
"is_parallel": true,
"self": 56.14821274199346,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.23229821000655,
"count": 4587,
"is_parallel": true,
"self": 125.23229821000655
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08701853200000187,
"count": 1,
"self": 0.0010015450000082637,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0860169869999936,
"count": 1,
"self": 0.0860169869999936
}
}
}
}
}
}
}