SnowballTarget / run_logs /timers.json
isotnek's picture
pushing SnowballTarget agent
13a9afd
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9510548710823059,
"min": 0.9435945749282837,
"max": 2.8622326850891113,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9080.671875,
"min": 9080.671875,
"max": 29343.609375,
"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": 13.16894817352295,
"min": 0.3109310269355774,
"max": 13.196495056152344,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2567.94482421875,
"min": 60.32061767578125,
"max": 2692.0849609375,
"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": 0.13881977383402508,
"min": 0.13190720896947788,
"max": 0.14783563009105444,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.5552790953361003,
"min": 0.546123782701483,
"max": 0.7294628474879645,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19596179756427218,
"min": 0.11660325805066166,
"max": 0.29154955987435055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7838471902570887,
"min": 0.4664130322026466,
"max": 1.2993175112568889,
"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": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.295454545454547,
"min": 3.4545454545454546,
"max": 26.12727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1113.0,
"min": 152.0,
"max": 1437.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.295454545454547,
"min": 3.4545454545454546,
"max": 26.12727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1113.0,
"min": 152.0,
"max": 1437.0,
"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": "1704216681",
"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": "1704217274"
},
"total": 592.8251022259999,
"count": 1,
"self": 0.44143129499980205,
"children": {
"run_training.setup": {
"total": 0.07897509999997965,
"count": 1,
"self": 0.07897509999997965
},
"TrainerController.start_learning": {
"total": 592.3046958310001,
"count": 1,
"self": 0.5967840589987645,
"children": {
"TrainerController._reset_env": {
"total": 3.589609166000173,
"count": 1,
"self": 3.589609166000173
},
"TrainerController.advance": {
"total": 588.0280491490012,
"count": 18199,
"self": 0.29119067000624455,
"children": {
"env_step": {
"total": 587.7368584789949,
"count": 18199,
"self": 445.9269103109539,
"children": {
"SubprocessEnvManager._take_step": {
"total": 141.5066746080363,
"count": 18199,
"self": 1.5441777820190055,
"children": {
"TorchPolicy.evaluate": {
"total": 139.9624968260173,
"count": 18199,
"self": 139.9624968260173
}
}
},
"workers": {
"total": 0.30327356000475447,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 591.0804071680275,
"count": 18199,
"is_parallel": true,
"self": 355.33685575303093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005126176999965537,
"count": 1,
"is_parallel": true,
"self": 0.0031348869999874296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019912899999781075,
"count": 10,
"is_parallel": true,
"self": 0.0019912899999781075
}
}
},
"UnityEnvironment.step": {
"total": 0.041596006999952806,
"count": 1,
"is_parallel": true,
"self": 0.0006883569999445172,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004498880000483041,
"count": 1,
"is_parallel": true,
"self": 0.0004498880000483041
},
"communicator.exchange": {
"total": 0.03834186199992473,
"count": 1,
"is_parallel": true,
"self": 0.03834186199992473
},
"steps_from_proto": {
"total": 0.0021159000000352535,
"count": 1,
"is_parallel": true,
"self": 0.00038312000015139347,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00173277999988386,
"count": 10,
"is_parallel": true,
"self": 0.00173277999988386
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 235.74355141499655,
"count": 18198,
"is_parallel": true,
"self": 11.117371948978644,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.741031168990958,
"count": 18198,
"is_parallel": true,
"self": 5.741031168990958
},
"communicator.exchange": {
"total": 182.31833593403826,
"count": 18198,
"is_parallel": true,
"self": 182.31833593403826
},
"steps_from_proto": {
"total": 36.566812362988685,
"count": 18198,
"is_parallel": true,
"self": 6.800837796099586,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.7659745668891,
"count": 181980,
"is_parallel": true,
"self": 29.7659745668891
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013218799995229347,
"count": 1,
"self": 0.00013218799995229347,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 582.1490768809279,
"count": 694823,
"is_parallel": true,
"self": 14.96714664885485,
"children": {
"process_trajectory": {
"total": 247.66814921007267,
"count": 694823,
"is_parallel": true,
"self": 246.88957868507237,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7785705250003048,
"count": 4,
"is_parallel": true,
"self": 0.7785705250003048
}
}
},
"_update_policy": {
"total": 319.51378102200033,
"count": 90,
"is_parallel": true,
"self": 54.83384363804703,
"children": {
"TorchPPOOptimizer.update": {
"total": 264.6799373839533,
"count": 18357,
"is_parallel": true,
"self": 264.6799373839533
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09012126900006479,
"count": 1,
"self": 0.0009708369998406852,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0891504320002241,
"count": 1,
"self": 0.0891504320002241
}
}
}
}
}
}
}