bunnyTech's picture
First Push
77a0d8a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9917888045310974,
"min": 0.9917888045310974,
"max": 2.8696720600128174,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9513.23828125,
"min": 9513.23828125,
"max": 29514.578125,
"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": 12.715209007263184,
"min": 0.3112587630748749,
"max": 12.715209007263184,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2479.4658203125,
"min": 60.38420104980469,
"max": 2592.430908203125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.0696355780505566,
"min": 0.06172608707542988,
"max": 0.07362891986244814,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2785423122022264,
"min": 0.2469043483017195,
"max": 0.3681445993122407,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.23030425462068296,
"min": 0.10950060800407266,
"max": 0.27692902912111844,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9212170184827319,
"min": 0.43800243201629063,
"max": 1.3846451456055922,
"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": 3.2954545454545454,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1100.0,
"min": 145.0,
"max": 1382.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.0,
"min": 3.2954545454545454,
"max": 25.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1100.0,
"min": 145.0,
"max": 1382.0,
"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": "1711097344",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/dl/miniconda3/envs/huggydog/bin/mlagents-learn ./ml-agents/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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711097678"
},
"total": 334.3048628640827,
"count": 1,
"self": 0.37034383602440357,
"children": {
"run_training.setup": {
"total": 0.0174948840867728,
"count": 1,
"self": 0.0174948840867728
},
"TrainerController.start_learning": {
"total": 333.9170241439715,
"count": 1,
"self": 0.3090185262262821,
"children": {
"TrainerController._reset_env": {
"total": 1.9709727079607546,
"count": 1,
"self": 1.9709727079607546
},
"TrainerController.advance": {
"total": 331.578330013901,
"count": 18204,
"self": 0.15061585884541273,
"children": {
"env_step": {
"total": 331.4277141550556,
"count": 18204,
"self": 256.6523502559867,
"children": {
"SubprocessEnvManager._take_step": {
"total": 74.6251242114231,
"count": 18204,
"self": 0.8517903853207827,
"children": {
"TorchPolicy.evaluate": {
"total": 73.77333382610232,
"count": 18204,
"self": 73.77333382610232
}
}
},
"workers": {
"total": 0.15023968764580786,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 333.30148928868584,
"count": 18204,
"is_parallel": true,
"self": 146.01473601767793,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0033826089929789305,
"count": 1,
"is_parallel": true,
"self": 0.0009691596496850252,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024134493432939053,
"count": 10,
"is_parallel": true,
"self": 0.0024134493432939053
}
}
},
"UnityEnvironment.step": {
"total": 0.02853315696120262,
"count": 1,
"is_parallel": true,
"self": 0.0005694681312888861,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004914968740195036,
"count": 1,
"is_parallel": true,
"self": 0.0004914968740195036
},
"communicator.exchange": {
"total": 0.025758052011951804,
"count": 1,
"is_parallel": true,
"self": 0.025758052011951804
},
"steps_from_proto": {
"total": 0.0017141399439424276,
"count": 1,
"is_parallel": true,
"self": 0.0003552024718374014,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013589374721050262,
"count": 10,
"is_parallel": true,
"self": 0.0013589374721050262
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 187.2867532710079,
"count": 18203,
"is_parallel": true,
"self": 8.030780698172748,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.2565964728128165,
"count": 18203,
"is_parallel": true,
"self": 4.2565964728128165
},
"communicator.exchange": {
"total": 150.33937163231894,
"count": 18203,
"is_parallel": true,
"self": 150.33937163231894
},
"steps_from_proto": {
"total": 24.660004467703402,
"count": 18203,
"is_parallel": true,
"self": 4.626991140190512,
"children": {
"_process_rank_one_or_two_observation": {
"total": 20.03301332751289,
"count": 182030,
"is_parallel": true,
"self": 20.03301332751289
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001511010341346264,
"count": 1,
"self": 0.0001511010341346264,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 331.0610724487342,
"count": 149456,
"is_parallel": true,
"self": 1.853057075291872,
"children": {
"process_trajectory": {
"total": 190.864762396086,
"count": 149456,
"is_parallel": true,
"self": 190.40897874813527,
"children": {
"RLTrainer._checkpoint": {
"total": 0.45578364795073867,
"count": 4,
"is_parallel": true,
"self": 0.45578364795073867
}
}
},
"_update_policy": {
"total": 138.34325297735631,
"count": 90,
"is_parallel": true,
"self": 26.592664469964802,
"children": {
"TorchPPOOptimizer.update": {
"total": 111.75058850739151,
"count": 4587,
"is_parallel": true,
"self": 111.75058850739151
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.05855179484933615,
"count": 1,
"self": 0.0005839429795742035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.057967851869761944,
"count": 1,
"self": 0.057967851869761944
}
}
}
}
}
}
}