ManarAli's picture
initial training of snowballTarget with ppo
73c86c3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0745247602462769,
"min": 1.0745247602462769,
"max": 2.864912271499634,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10295.021484375,
"min": 10295.021484375,
"max": 29371.080078125,
"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": 12.657013893127441,
"min": 0.3827759623527527,
"max": 12.657013893127441,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.11767578125,
"min": 74.25853729248047,
"max": 2569.335693359375,
"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": 0.07129288859797787,
"min": 0.06535340952995124,
"max": 0.0781613022382397,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2851715543919115,
"min": 0.2686795904305119,
"max": 0.37011256981949214,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20782906591307884,
"min": 0.11718162840606608,
"max": 0.2849094428706403,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8313162636523154,
"min": 0.4687265136242643,
"max": 1.3754597428966973,
"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": 24.363636363636363,
"min": 3.2954545454545454,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1072.0,
"min": 145.0,
"max": 1374.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.363636363636363,
"min": 3.2954545454545454,
"max": 25.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1072.0,
"min": 145.0,
"max": 1374.0,
"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": "1680444265",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget2 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680444725"
},
"total": 460.12605679100034,
"count": 1,
"self": 0.7573387190000176,
"children": {
"run_training.setup": {
"total": 0.16248458800009757,
"count": 1,
"self": 0.16248458800009757
},
"TrainerController.start_learning": {
"total": 459.2062334840002,
"count": 1,
"self": 0.5266141750057614,
"children": {
"TrainerController._reset_env": {
"total": 5.277088817000276,
"count": 1,
"self": 5.277088817000276
},
"TrainerController.advance": {
"total": 453.1874515199943,
"count": 18222,
"self": 0.25346898802490614,
"children": {
"env_step": {
"total": 452.9339825319694,
"count": 18222,
"self": 330.88382330003833,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.77864319699393,
"count": 18222,
"self": 1.6408232520707315,
"children": {
"TorchPolicy.evaluate": {
"total": 120.1378199449232,
"count": 18222,
"self": 120.1378199449232
}
}
},
"workers": {
"total": 0.27151603493712173,
"count": 18222,
"self": 0.0,
"children": {
"worker_root": {
"total": 457.7296964599145,
"count": 18222,
"is_parallel": true,
"self": 214.72757357585988,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002581637999810482,
"count": 1,
"is_parallel": true,
"self": 0.0006703110002490575,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019113269995614246,
"count": 10,
"is_parallel": true,
"self": 0.0019113269995614246
}
}
},
"UnityEnvironment.step": {
"total": 0.03533171999970364,
"count": 1,
"is_parallel": true,
"self": 0.0003855909990306827,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035467700035951566,
"count": 1,
"is_parallel": true,
"self": 0.00035467700035951566
},
"communicator.exchange": {
"total": 0.03315164200012077,
"count": 1,
"is_parallel": true,
"self": 0.03315164200012077
},
"steps_from_proto": {
"total": 0.001439810000192665,
"count": 1,
"is_parallel": true,
"self": 0.00035932800028604106,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001080481999906624,
"count": 10,
"is_parallel": true,
"self": 0.001080481999906624
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 243.00212288405464,
"count": 18221,
"is_parallel": true,
"self": 9.96113539399039,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.424335512015205,
"count": 18221,
"is_parallel": true,
"self": 5.424335512015205
},
"communicator.exchange": {
"total": 195.98732772303174,
"count": 18221,
"is_parallel": true,
"self": 195.98732772303174
},
"steps_from_proto": {
"total": 31.62932425501731,
"count": 18221,
"is_parallel": true,
"self": 6.1391066470196165,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.490217607997693,
"count": 182210,
"is_parallel": true,
"self": 25.490217607997693
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013405000026978087,
"count": 1,
"self": 0.00013405000026978087,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 449.5762817289583,
"count": 391713,
"is_parallel": true,
"self": 9.929051698284184,
"children": {
"process_trajectory": {
"total": 247.3599622196757,
"count": 391713,
"is_parallel": true,
"self": 245.71722928567578,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6427329339999233,
"count": 4,
"is_parallel": true,
"self": 1.6427329339999233
}
}
},
"_update_policy": {
"total": 192.2872678109984,
"count": 90,
"is_parallel": true,
"self": 71.93730058800156,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.34996722299684,
"count": 4587,
"is_parallel": true,
"self": 120.34996722299684
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.21494492199963133,
"count": 1,
"self": 0.0011560869997992995,
"children": {
"RLTrainer._checkpoint": {
"total": 0.21378883499983203,
"count": 1,
"self": 0.21378883499983203
}
}
}
}
}
}
}