atorre's picture
First training of PPO agent on SnowballTarget environment.
90e9ddb
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8087154030799866,
"min": 0.8087154030799866,
"max": 2.87198805809021,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7712.71875,
"min": 7712.71875,
"max": 29569.98828125,
"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": 12.482733726501465,
"min": 0.35245320200920105,
"max": 12.482733726501465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2434.133056640625,
"min": 68.37592315673828,
"max": 2535.87646484375,
"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": 0.0737230419084988,
"min": 0.060572049622001654,
"max": 0.07670909437423974,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2948921676339952,
"min": 0.25168726781878065,
"max": 0.3835454718711987,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19191460691246331,
"min": 0.1070490307471368,
"max": 0.294021538718074,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7676584276498533,
"min": 0.4281961229885472,
"max": 1.47010769359037,
"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": 24.681818181818183,
"min": 2.8863636363636362,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1086.0,
"min": 127.0,
"max": 1351.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.681818181818183,
"min": 2.8863636363636362,
"max": 24.681818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1086.0,
"min": 127.0,
"max": 1351.0,
"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": "1673941377",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics --force",
"mlagents_version": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673941944"
},
"total": 567.1588809569998,
"count": 1,
"self": 0.6461592559994642,
"children": {
"run_training.setup": {
"total": 0.14211032000002888,
"count": 1,
"self": 0.14211032000002888
},
"TrainerController.start_learning": {
"total": 566.3706113810003,
"count": 1,
"self": 0.8197631960065337,
"children": {
"TrainerController._reset_env": {
"total": 10.019188577000023,
"count": 1,
"self": 10.019188577000023
},
"TrainerController.advance": {
"total": 555.2024090139939,
"count": 18211,
"self": 0.4340760940153814,
"children": {
"env_step": {
"total": 554.7683329199785,
"count": 18211,
"self": 419.53077298000926,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.8149154949415,
"count": 18211,
"self": 2.2135619419354953,
"children": {
"TorchPolicy.evaluate": {
"total": 132.601353553006,
"count": 18211,
"self": 21.671737697031404,
"children": {
"TorchPolicy.sample_actions": {
"total": 110.92961585597459,
"count": 18211,
"self": 110.92961585597459
}
}
}
}
},
"workers": {
"total": 0.4226444450277995,
"count": 18211,
"self": 0.0,
"children": {
"worker_root": {
"total": 564.302774801004,
"count": 18211,
"is_parallel": true,
"self": 252.8394644930554,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.008409036999637465,
"count": 1,
"is_parallel": true,
"self": 0.004914334998829872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0034947020008075924,
"count": 10,
"is_parallel": true,
"self": 0.0034947020008075924
}
}
},
"UnityEnvironment.step": {
"total": 0.043924952999987,
"count": 1,
"is_parallel": true,
"self": 0.0007053039998936583,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00045333800017033354,
"count": 1,
"is_parallel": true,
"self": 0.00045333800017033354
},
"communicator.exchange": {
"total": 0.04025137899998299,
"count": 1,
"is_parallel": true,
"self": 0.04025137899998299
},
"steps_from_proto": {
"total": 0.0025149319999400177,
"count": 1,
"is_parallel": true,
"self": 0.0005169589999240998,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001997973000015918,
"count": 10,
"is_parallel": true,
"self": 0.001997973000015918
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 311.46331030794863,
"count": 18210,
"is_parallel": true,
"self": 12.666697237909375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.554363085021578,
"count": 18210,
"is_parallel": true,
"self": 7.554363085021578
},
"communicator.exchange": {
"total": 243.47783153198452,
"count": 18210,
"is_parallel": true,
"self": 243.47783153198452
},
"steps_from_proto": {
"total": 47.76441845303316,
"count": 18210,
"is_parallel": true,
"self": 9.95746614890686,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.8069523041263,
"count": 182100,
"is_parallel": true,
"self": 37.8069523041263
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.6740999752946664e-05,
"count": 1,
"self": 5.6740999752946664e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 550.159477769997,
"count": 562881,
"is_parallel": true,
"self": 14.986800978045267,
"children": {
"process_trajectory": {
"total": 304.36453699395133,
"count": 562881,
"is_parallel": true,
"self": 302.95086230095103,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4136746930003028,
"count": 4,
"is_parallel": true,
"self": 1.4136746930003028
}
}
},
"_update_policy": {
"total": 230.8081397980004,
"count": 90,
"is_parallel": true,
"self": 59.82484272600959,
"children": {
"TorchPPOOptimizer.update": {
"total": 170.98329707199082,
"count": 4587,
"is_parallel": true,
"self": 170.98329707199082
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.3291938530001062,
"count": 1,
"self": 0.002119316000062099,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3270745370000441,
"count": 1,
"self": 0.3270745370000441
}
}
}
}
}
}
}