Paperbag's picture
First training of SnowballTarget
4f0b8a7
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.942276120185852,
"min": 0.942276120185852,
"max": 2.866274118423462,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9038.3125,
"min": 9038.3125,
"max": 29479.62890625,
"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": 13.118900299072266,
"min": 0.4082595705986023,
"max": 13.118900299072266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2558.185546875,
"min": 79.20235443115234,
"max": 2673.76416015625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06967958334694142,
"min": 0.06181785852885715,
"max": 0.07277820325798887,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2787183333877657,
"min": 0.2586571904328451,
"max": 0.3602014497851533,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19019951262310442,
"min": 0.13190243729417594,
"max": 0.29917546588124017,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7607980504924177,
"min": 0.5276097491767038,
"max": 1.3673451829190348,
"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": 3.840909090909091,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 169.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.840909090909091,
"max": 26.068181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 169.0,
"max": 1386.0,
"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": "1677915368",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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=SnowballTarget1 --no-graphics",
"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": "1.22.4",
"end_time_seconds": "1677915825"
},
"total": 456.45065866500005,
"count": 1,
"self": 0.6999780490000376,
"children": {
"run_training.setup": {
"total": 0.11585869300000695,
"count": 1,
"self": 0.11585869300000695
},
"TrainerController.start_learning": {
"total": 455.634821923,
"count": 1,
"self": 0.5390580519929244,
"children": {
"TrainerController._reset_env": {
"total": 10.317456015000005,
"count": 1,
"self": 10.317456015000005
},
"TrainerController.advance": {
"total": 444.5840750790073,
"count": 18216,
"self": 0.2526289230045222,
"children": {
"env_step": {
"total": 444.33144615600276,
"count": 18216,
"self": 305.9447228480069,
"children": {
"SubprocessEnvManager._take_step": {
"total": 138.12595044098896,
"count": 18216,
"self": 1.4584624819848955,
"children": {
"TorchPolicy.evaluate": {
"total": 136.66748795900406,
"count": 18216,
"self": 31.012460025001047,
"children": {
"TorchPolicy.sample_actions": {
"total": 105.65502793400302,
"count": 18216,
"self": 105.65502793400302
}
}
}
}
},
"workers": {
"total": 0.26077286700686386,
"count": 18216,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.167706147003,
"count": 18216,
"is_parallel": true,
"self": 223.16210550500568,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006053170000001273,
"count": 1,
"is_parallel": true,
"self": 0.0037735650000172427,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022796049999840307,
"count": 10,
"is_parallel": true,
"self": 0.0022796049999840307
}
}
},
"UnityEnvironment.step": {
"total": 0.034203593000000865,
"count": 1,
"is_parallel": true,
"self": 0.0005743700000095942,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003343650000147136,
"count": 1,
"is_parallel": true,
"self": 0.0003343650000147136
},
"communicator.exchange": {
"total": 0.03139570899998034,
"count": 1,
"is_parallel": true,
"self": 0.03139570899998034
},
"steps_from_proto": {
"total": 0.0018991489999962141,
"count": 1,
"is_parallel": true,
"self": 0.00042980399996395136,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014693450000322628,
"count": 10,
"is_parallel": true,
"self": 0.0014693450000322628
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 231.00560064199732,
"count": 18215,
"is_parallel": true,
"self": 9.613614399996464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.131901178998589,
"count": 18215,
"is_parallel": true,
"self": 5.131901178998589
},
"communicator.exchange": {
"total": 185.95607658900036,
"count": 18215,
"is_parallel": true,
"self": 185.95607658900036
},
"steps_from_proto": {
"total": 30.304008474001904,
"count": 18215,
"is_parallel": true,
"self": 6.4984325290148774,
"children": {
"_process_rank_one_or_two_observation": {
"total": 23.805575944987027,
"count": 182150,
"is_parallel": true,
"self": 23.805575944987027
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013935199990555702,
"count": 1,
"self": 0.00013935199990555702,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 441.2290762570017,
"count": 405202,
"is_parallel": true,
"self": 10.003930605035407,
"children": {
"process_trajectory": {
"total": 252.07321387496694,
"count": 405202,
"is_parallel": true,
"self": 251.13533258596698,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9378812889999608,
"count": 4,
"is_parallel": true,
"self": 0.9378812889999608
}
}
},
"_update_policy": {
"total": 179.1519317769993,
"count": 90,
"is_parallel": true,
"self": 62.86366095800079,
"children": {
"TorchPPOOptimizer.update": {
"total": 116.28827081899851,
"count": 4587,
"is_parallel": true,
"self": 116.28827081899851
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1940934249998918,
"count": 1,
"self": 0.0011054969999122477,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19298792799997955,
"count": 1,
"self": 0.19298792799997955
}
}
}
}
}
}
}