conlan's picture
First Push
e4b58ac verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9681368470191956,
"min": 0.9681368470191956,
"max": 2.86319899559021,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9233.12109375,
"min": 9233.12109375,
"max": 29510.9921875,
"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": 13.014107704162598,
"min": 0.2522284984588623,
"max": 13.014107704162598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2537.7509765625,
"min": 48.93232727050781,
"max": 2598.186279296875,
"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": 0.06739682980589672,
"min": 0.06541884260288641,
"max": 0.07447218374599128,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26958731922358686,
"min": 0.2685332445606964,
"max": 0.3638467404999378,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19122165887086998,
"min": 0.10275501745191458,
"max": 0.2882019608044157,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7648866354834799,
"min": 0.4110200698076583,
"max": 1.4410098040220785,
"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": 25.886363636363637,
"min": 3.0681818181818183,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 135.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.0681818181818183,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 135.0,
"max": 1410.0,
"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": "1713558191",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/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": "1713558646"
},
"total": 455.319823496,
"count": 1,
"self": 0.47531038400006764,
"children": {
"run_training.setup": {
"total": 0.0517410679999557,
"count": 1,
"self": 0.0517410679999557
},
"TrainerController.start_learning": {
"total": 454.792772044,
"count": 1,
"self": 0.6067574990112234,
"children": {
"TrainerController._reset_env": {
"total": 3.6737637219999897,
"count": 1,
"self": 3.6737637219999897
},
"TrainerController.advance": {
"total": 450.4190157279887,
"count": 18198,
"self": 0.27797836599870607,
"children": {
"env_step": {
"total": 450.14103736199,
"count": 18198,
"self": 293.7639850449983,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.09017481999797,
"count": 18198,
"self": 1.4741354390080232,
"children": {
"TorchPolicy.evaluate": {
"total": 154.61603938098995,
"count": 18198,
"self": 154.61603938098995
}
}
},
"workers": {
"total": 0.2868774969937249,
"count": 18198,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.5605009400008,
"count": 18198,
"is_parallel": true,
"self": 225.56010520399866,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005670683999937864,
"count": 1,
"is_parallel": true,
"self": 0.004097117000128492,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015735669998093726,
"count": 10,
"is_parallel": true,
"self": 0.0015735669998093726
}
}
},
"UnityEnvironment.step": {
"total": 0.0832489430000578,
"count": 1,
"is_parallel": true,
"self": 0.0007063889999017192,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037630300005275785,
"count": 1,
"is_parallel": true,
"self": 0.00037630300005275785
},
"communicator.exchange": {
"total": 0.08007850500007407,
"count": 1,
"is_parallel": true,
"self": 0.08007850500007407
},
"steps_from_proto": {
"total": 0.002087746000029256,
"count": 1,
"is_parallel": true,
"self": 0.00043302800008859776,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001654717999940658,
"count": 10,
"is_parallel": true,
"self": 0.001654717999940658
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.00039573600213,
"count": 18197,
"is_parallel": true,
"self": 10.343116481001289,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.394816439006377,
"count": 18197,
"is_parallel": true,
"self": 5.394816439006377
},
"communicator.exchange": {
"total": 178.37716460899514,
"count": 18197,
"is_parallel": true,
"self": 178.37716460899514
},
"steps_from_proto": {
"total": 33.88529820699932,
"count": 18197,
"is_parallel": true,
"self": 6.524629284976072,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.36066892202325,
"count": 181970,
"is_parallel": true,
"self": 27.36066892202325
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001767500000369182,
"count": 1,
"self": 0.0001767500000369182,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 444.86986974799254,
"count": 685493,
"is_parallel": true,
"self": 14.583300132988938,
"children": {
"process_trajectory": {
"total": 245.69656353400387,
"count": 685493,
"is_parallel": true,
"self": 245.12591132000375,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5706522140001198,
"count": 4,
"is_parallel": true,
"self": 0.5706522140001198
}
}
},
"_update_policy": {
"total": 184.59000608099973,
"count": 90,
"is_parallel": true,
"self": 55.13759314699905,
"children": {
"TorchPPOOptimizer.update": {
"total": 129.45241293400068,
"count": 4587,
"is_parallel": true,
"self": 129.45241293400068
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0930583450000313,
"count": 1,
"self": 0.0010006260000636757,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09205771899996762,
"count": 1,
"self": 0.09205771899996762
}
}
}
}
}
}
}