feysahin's picture
32-batchsize
3b33bb7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9838725328445435,
"min": 0.965241551399231,
"max": 2.866785764694214,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9729.515625,
"min": 9625.013671875,
"max": 29295.68359375,
"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": 13.067357063293457,
"min": 0.30062130093574524,
"max": 13.067357063293457,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 4521.3056640625,
"min": 103.71434783935547,
"max": 4587.3818359375,
"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": 0.09833402143611274,
"min": 0.08959242349465414,
"max": 0.10495804121142012,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.39333608574445095,
"min": 0.3649836925311213,
"max": 0.5207478383452543,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.175560578356917,
"min": 0.11516721773476507,
"max": 0.23881364748904518,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.702242313427668,
"min": 0.4606688709390603,
"max": 1.1811038187029315,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000007e-06,
"min": 8.082097306000007e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400003e-05,
"min": 3.232838922400003e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269399999999997,
"min": 0.10269399999999997,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077599999999986,
"min": 0.41077599999999986,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.004864970599999999,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828000000003,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.84090909090909,
"min": 3.75,
"max": 26.0,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1137.0,
"min": 165.0,
"max": 1430.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.84090909090909,
"min": 3.75,
"max": 26.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1137.0,
"min": 165.0,
"max": 1430.0,
"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": "1717234092",
"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=SnowballTarget2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1717234604"
},
"total": 512.127364681,
"count": 1,
"self": 0.4260075149995828,
"children": {
"run_training.setup": {
"total": 0.05430630900036704,
"count": 1,
"self": 0.05430630900036704
},
"TrainerController.start_learning": {
"total": 511.64705085700007,
"count": 1,
"self": 0.619859824996638,
"children": {
"TrainerController._reset_env": {
"total": 2.5237525529996674,
"count": 1,
"self": 2.5237525529996674
},
"TrainerController.advance": {
"total": 508.4140232240038,
"count": 18200,
"self": 0.28823994402273456,
"children": {
"env_step": {
"total": 508.1257832799811,
"count": 18200,
"self": 373.0337538399799,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.7856456429663,
"count": 18200,
"self": 1.7443572609772673,
"children": {
"TorchPolicy.evaluate": {
"total": 133.04128838198903,
"count": 18200,
"self": 133.04128838198903
}
}
},
"workers": {
"total": 0.3063837970348686,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 510.2053330989693,
"count": 18200,
"is_parallel": true,
"self": 283.7239173809576,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022093829998084402,
"count": 1,
"is_parallel": true,
"self": 0.000627141000222764,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015822419995856762,
"count": 10,
"is_parallel": true,
"self": 0.0015822419995856762
}
}
},
"UnityEnvironment.step": {
"total": 0.07990689799999018,
"count": 1,
"is_parallel": true,
"self": 0.0006111320003583387,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003600850000111677,
"count": 1,
"is_parallel": true,
"self": 0.0003600850000111677
},
"communicator.exchange": {
"total": 0.07718432899991967,
"count": 1,
"is_parallel": true,
"self": 0.07718432899991967
},
"steps_from_proto": {
"total": 0.0017513519997010008,
"count": 1,
"is_parallel": true,
"self": 0.00033043599978554994,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014209159999154508,
"count": 10,
"is_parallel": true,
"self": 0.0014209159999154508
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.4814157180117,
"count": 18199,
"is_parallel": true,
"self": 10.214919567026755,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.34711932500295,
"count": 18199,
"is_parallel": true,
"self": 5.34711932500295
},
"communicator.exchange": {
"total": 177.7891860109803,
"count": 18199,
"is_parallel": true,
"self": 177.7891860109803
},
"steps_from_proto": {
"total": 33.1301908150017,
"count": 18199,
"is_parallel": true,
"self": 6.313989595913881,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.816201219087816,
"count": 181990,
"is_parallel": true,
"self": 26.816201219087816
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00018463100013832445,
"count": 1,
"self": 0.00018463100013832445,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 501.67785952741633,
"count": 804214,
"is_parallel": true,
"self": 16.4597098723998,
"children": {
"process_trajectory": {
"total": 300.43437867401826,
"count": 804214,
"is_parallel": true,
"self": 299.6356772560184,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7987014179998368,
"count": 4,
"is_parallel": true,
"self": 0.7987014179998368
}
}
},
"_update_policy": {
"total": 184.78377098099827,
"count": 90,
"is_parallel": true,
"self": 51.24470552498542,
"children": {
"TorchPPOOptimizer.update": {
"total": 133.53906545601285,
"count": 9177,
"is_parallel": true,
"self": 133.53906545601285
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08923062399981063,
"count": 1,
"self": 0.00097448099995745,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08825614299985318,
"count": 1,
"self": 0.08825614299985318
}
}
}
}
}
}
}