SnowballTarget5 / run_logs /timers.json
baronase's picture
2nd try, time_horizon:32
fee11ab verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9985322952270508,
"min": 0.992946207523346,
"max": 2.8741352558135986,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9841.5341796875,
"min": 9841.5341796875,
"max": 29339.173828125,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9984.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9984.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.99207592010498,
"min": 0.25616219639778137,
"max": 12.99207592010498,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4495.25830078125,
"min": 88.37596130371094,
"max": 4541.1962890625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06311576881682199,
"min": 0.06182950255141466,
"max": 0.07774278132423848,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.25246307526728795,
"min": 0.25246307526728795,
"max": 0.36562895962817815,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19458738341927528,
"min": 0.0990260931327665,
"max": 0.26105213588943665,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7783495336771011,
"min": 0.396104372531066,
"max": 1.2331008157309364,
"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": 25.272727272727273,
"min": 3.2954545454545454,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1421.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.272727272727273,
"min": 3.2954545454545454,
"max": 25.836363636363636,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1112.0,
"min": 145.0,
"max": 1421.0,
"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": "1739015401",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=my_run_id --no-graphics --force",
"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": "1739015864"
},
"total": 463.45598870899994,
"count": 1,
"self": 0.4250834380000015,
"children": {
"run_training.setup": {
"total": 0.0212474990003102,
"count": 1,
"self": 0.0212474990003102
},
"TrainerController.start_learning": {
"total": 463.0096577719996,
"count": 1,
"self": 0.3859600709429287,
"children": {
"TrainerController._reset_env": {
"total": 1.9376640410000618,
"count": 1,
"self": 1.9376640410000618
},
"TrainerController.advance": {
"total": 460.59248971305533,
"count": 18192,
"self": 0.4063884110564686,
"children": {
"env_step": {
"total": 322.5626136260171,
"count": 18192,
"self": 245.0801933370194,
"children": {
"SubprocessEnvManager._take_step": {
"total": 77.24882868398163,
"count": 18192,
"self": 1.3689781150214912,
"children": {
"TorchPolicy.evaluate": {
"total": 75.87985056896014,
"count": 18192,
"self": 75.87985056896014
}
}
},
"workers": {
"total": 0.23359160501604492,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 461.4384178079654,
"count": 18192,
"is_parallel": true,
"self": 246.82315045796713,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002171744000406761,
"count": 1,
"is_parallel": true,
"self": 0.0006821830020271591,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001489560998379602,
"count": 10,
"is_parallel": true,
"self": 0.001489560998379602
}
}
},
"UnityEnvironment.step": {
"total": 0.034984853000423755,
"count": 1,
"is_parallel": true,
"self": 0.0005909100000280887,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00038448899977083784,
"count": 1,
"is_parallel": true,
"self": 0.00038448899977083784
},
"communicator.exchange": {
"total": 0.03221951200066542,
"count": 1,
"is_parallel": true,
"self": 0.03221951200066542
},
"steps_from_proto": {
"total": 0.0017899419999594102,
"count": 1,
"is_parallel": true,
"self": 0.00035050699898420135,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014394350009752088,
"count": 10,
"is_parallel": true,
"self": 0.0014394350009752088
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 214.61526734999825,
"count": 18191,
"is_parallel": true,
"self": 9.955182770026113,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.758412056036832,
"count": 18191,
"is_parallel": true,
"self": 5.758412056036832
},
"communicator.exchange": {
"total": 165.37675128694082,
"count": 18191,
"is_parallel": true,
"self": 165.37675128694082
},
"steps_from_proto": {
"total": 33.52492123699449,
"count": 18191,
"is_parallel": true,
"self": 6.077929993055477,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.44699124393901,
"count": 181910,
"is_parallel": true,
"self": 27.44699124393901
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 137.62348767598178,
"count": 18192,
"self": 0.4672868959187326,
"children": {
"process_trajectory": {
"total": 37.05739246905887,
"count": 18192,
"self": 36.65069941405909,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4066930549997778,
"count": 4,
"self": 0.4066930549997778
}
}
},
"_update_policy": {
"total": 100.09880831100418,
"count": 90,
"self": 40.685734841027624,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.41307346997655,
"count": 4587,
"self": 59.41307346997655
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.760005923453718e-07,
"count": 1,
"self": 9.760005923453718e-07
},
"TrainerController._save_models": {
"total": 0.09354297100071562,
"count": 1,
"self": 0.0012433800002327189,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0922995910004829,
"count": 1,
"self": 0.0922995910004829
}
}
}
}
}
}
}