stalaei's picture
First Push
c041261 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9193993806838989,
"min": 0.9193993806838989,
"max": 2.836681365966797,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8737.9716796875,
"min": 8737.9716796875,
"max": 28956.84375,
"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": 12.90727710723877,
"min": 0.430264413356781,
"max": 12.90727710723877,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2516.9189453125,
"min": 83.47129821777344,
"max": 2605.310791015625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06457184948368534,
"min": 0.06140367331054043,
"max": 0.0763913588187493,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25828739793474137,
"min": 0.24561469324216173,
"max": 0.3595780230608915,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21310786486548536,
"min": 0.13747872152781188,
"max": 0.3059148104021362,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8524314594619414,
"min": 0.5499148861112475,
"max": 1.5043098713253058,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.636363636363637,
"min": 3.590909090909091,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1128.0,
"min": 158.0,
"max": 1416.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.636363636363637,
"min": 3.590909090909091,
"max": 25.745454545454546,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1128.0,
"min": 158.0,
"max": 1416.0,
"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": "1743189357",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/home/stalaei/miniconda3/envs/DeepRL/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743189784"
},
"total": 426.3428282700479,
"count": 1,
"self": 0.6759515181183815,
"children": {
"run_training.setup": {
"total": 0.07032862899359316,
"count": 1,
"self": 0.07032862899359316
},
"TrainerController.start_learning": {
"total": 425.5965481229359,
"count": 1,
"self": 0.23719100700691342,
"children": {
"TrainerController._reset_env": {
"total": 3.314810729934834,
"count": 1,
"self": 3.314810729934834
},
"TrainerController.advance": {
"total": 421.89305476506706,
"count": 18192,
"self": 0.24064493691548705,
"children": {
"env_step": {
"total": 309.33407319081016,
"count": 18192,
"self": 240.56850601057522,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.61079594516195,
"count": 18192,
"self": 0.8201580671593547,
"children": {
"TorchPolicy.evaluate": {
"total": 67.7906378780026,
"count": 18192,
"self": 67.7906378780026
}
}
},
"workers": {
"total": 0.1547712350729853,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 424.88801611657254,
"count": 18192,
"is_parallel": true,
"self": 201.1765321037965,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001987130963243544,
"count": 1,
"is_parallel": true,
"self": 0.0005124277668073773,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014747031964361668,
"count": 10,
"is_parallel": true,
"self": 0.0014747031964361668
}
}
},
"UnityEnvironment.step": {
"total": 0.026488831965252757,
"count": 1,
"is_parallel": true,
"self": 0.00033767696004360914,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00026141898706555367,
"count": 1,
"is_parallel": true,
"self": 0.00026141898706555367
},
"communicator.exchange": {
"total": 0.02479995007161051,
"count": 1,
"is_parallel": true,
"self": 0.02479995007161051
},
"steps_from_proto": {
"total": 0.001089785946533084,
"count": 1,
"is_parallel": true,
"self": 0.00022211007308214903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008676758734509349,
"count": 10,
"is_parallel": true,
"self": 0.0008676758734509349
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.71148401277605,
"count": 18191,
"is_parallel": true,
"self": 5.809117040480487,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.14913456258364,
"count": 18191,
"is_parallel": true,
"self": 3.14913456258364
},
"communicator.exchange": {
"total": 196.77310874965042,
"count": 18191,
"is_parallel": true,
"self": 196.77310874965042
},
"steps_from_proto": {
"total": 17.98012366006151,
"count": 18191,
"is_parallel": true,
"self": 3.3415828658035025,
"children": {
"_process_rank_one_or_two_observation": {
"total": 14.638540794258006,
"count": 181910,
"is_parallel": true,
"self": 14.638540794258006
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 112.31833663734142,
"count": 18192,
"self": 0.2612625869223848,
"children": {
"process_trajectory": {
"total": 29.99163278262131,
"count": 18192,
"self": 29.543468650546856,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44816413207445294,
"count": 4,
"self": 0.44816413207445294
}
}
},
"_update_policy": {
"total": 82.06544126779772,
"count": 90,
"self": 28.011550523340702,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.05389074445702,
"count": 4587,
"self": 54.05389074445702
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.499482646584511e-07,
"count": 1,
"self": 8.499482646584511e-07
},
"TrainerController._save_models": {
"total": 0.1514907709788531,
"count": 1,
"self": 0.015253002988174558,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13623776799067855,
"count": 1,
"self": 0.13623776799067855
}
}
}
}
}
}
}