RicardoMorim's picture
First Push
a688048 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9969506859779358,
"min": 0.9737204313278198,
"max": 2.8681743144989014,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9475.01953125,
"min": 9475.01953125,
"max": 29278.322265625,
"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": 13.782757759094238,
"min": 0.2788407504558563,
"max": 13.782757759094238,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2687.6376953125,
"min": 54.0951042175293,
"max": 2789.8095703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.023021723405690864,
"min": 0.023021723405690864,
"max": 0.03772237515076995,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.09208689362276345,
"min": 0.09208689362276345,
"max": 0.18861187575384974,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16665415652096272,
"min": 0.1403747657313943,
"max": 0.4078444242477417,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6666166260838509,
"min": 0.5614990629255772,
"max": 1.927754420787096,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.3470097306000012e-05,
"min": 1.3470097306000012e-05,
"max": 0.0004864700027059999,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 5.388038922400005e-05,
"min": 5.388038922400005e-05,
"max": 0.0023086000382799995,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00027913060000000025,
"min": 0.00027913060000000025,
"max": 0.009729670600000002,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001116522400000001,
"min": 0.001116522400000001,
"max": 0.04617582799999999,
"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": 26.977272727272727,
"min": 3.6818181818181817,
"max": 26.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1187.0,
"min": 162.0,
"max": 1481.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.977272727272727,
"min": 3.6818181818181817,
"max": 26.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1187.0,
"min": 162.0,
"max": 1481.0,
"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": "1755104323",
"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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1755104753"
},
"total": 429.792741655,
"count": 1,
"self": 0.4409708009999349,
"children": {
"run_training.setup": {
"total": 0.030710123000062595,
"count": 1,
"self": 0.030710123000062595
},
"TrainerController.start_learning": {
"total": 429.321060731,
"count": 1,
"self": 0.3948691060056717,
"children": {
"TrainerController._reset_env": {
"total": 3.143105731999981,
"count": 1,
"self": 3.143105731999981
},
"TrainerController.advance": {
"total": 425.6358174959943,
"count": 18192,
"self": 0.39717370099754135,
"children": {
"env_step": {
"total": 326.06203120199393,
"count": 18192,
"self": 242.6518383129752,
"children": {
"SubprocessEnvManager._take_step": {
"total": 83.17532906101337,
"count": 18192,
"self": 1.3016077180120647,
"children": {
"TorchPolicy.evaluate": {
"total": 81.8737213430013,
"count": 18192,
"self": 81.8737213430013
}
}
},
"workers": {
"total": 0.2348638280053592,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 427.7987901259821,
"count": 18192,
"is_parallel": true,
"self": 214.56632210298812,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0063444820000313484,
"count": 1,
"is_parallel": true,
"self": 0.004059265000250889,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022852169997804594,
"count": 10,
"is_parallel": true,
"self": 0.0022852169997804594
}
}
},
"UnityEnvironment.step": {
"total": 0.03469184500011124,
"count": 1,
"is_parallel": true,
"self": 0.0005881460000409788,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003900789999988774,
"count": 1,
"is_parallel": true,
"self": 0.0003900789999988774
},
"communicator.exchange": {
"total": 0.031811203000074784,
"count": 1,
"is_parallel": true,
"self": 0.031811203000074784
},
"steps_from_proto": {
"total": 0.0019024169999966034,
"count": 1,
"is_parallel": true,
"self": 0.00040895099994031625,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014934660000562872,
"count": 10,
"is_parallel": true,
"self": 0.0014934660000562872
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 213.232468022994,
"count": 18191,
"is_parallel": true,
"self": 9.92974004398286,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.609983452006418,
"count": 18191,
"is_parallel": true,
"self": 5.609983452006418
},
"communicator.exchange": {
"total": 165.0164378160024,
"count": 18191,
"is_parallel": true,
"self": 165.0164378160024
},
"steps_from_proto": {
"total": 32.676306711002326,
"count": 18191,
"is_parallel": true,
"self": 5.9111552119899216,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.765151499012404,
"count": 181910,
"is_parallel": true,
"self": 26.765151499012404
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 99.1766125930028,
"count": 18192,
"self": 0.4985743219814367,
"children": {
"process_trajectory": {
"total": 43.310612471021045,
"count": 18192,
"self": 42.61808685402082,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6925256170002285,
"count": 4,
"self": 0.6925256170002285
}
}
},
"_update_policy": {
"total": 55.36742580000032,
"count": 90,
"self": 36.738354938002544,
"children": {
"TorchPPOOptimizer.update": {
"total": 18.629070861997775,
"count": 1080,
"self": 18.629070861997775
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.742999969195807e-06,
"count": 1,
"self": 7.742999969195807e-06
},
"TrainerController._save_models": {
"total": 0.14726065400009247,
"count": 1,
"self": 0.0017312550000951887,
"children": {
"RLTrainer._checkpoint": {
"total": 0.14552939899999728,
"count": 1,
"self": 0.14552939899999728
}
}
}
}
}
}
}