zeevikal's picture
Push ppo-SnowballTarget
59b48d2 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1069203615188599,
"min": 1.1069203615188599,
"max": 2.8728950023651123,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10605.404296875,
"min": 10605.404296875,
"max": 29484.521484375,
"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": 11.882935523986816,
"min": 0.37459370493888855,
"max": 11.882935523986816,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2317.17236328125,
"min": 72.67118072509766,
"max": 2394.396484375,
"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": 0.07706962661148853,
"min": 0.06363737555932625,
"max": 0.07742626861048242,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3082785064459541,
"min": 0.254549502237305,
"max": 0.3871313430524121,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20911567051913227,
"min": 0.12062451450665501,
"max": 0.28380615519834496,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8364626820765291,
"min": 0.48249805802662005,
"max": 1.384913301935383,
"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": 23.568181818181817,
"min": 3.340909090909091,
"max": 23.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1037.0,
"min": 147.0,
"max": 1307.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.568181818181817,
"min": 3.340909090909091,
"max": 23.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1037.0,
"min": 147.0,
"max": 1307.0,
"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": "1722240091",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722240473"
},
"total": 381.664813184,
"count": 1,
"self": 0.32204169500005264,
"children": {
"run_training.setup": {
"total": 0.05845910099998264,
"count": 1,
"self": 0.05845910099998264
},
"TrainerController.start_learning": {
"total": 381.284312388,
"count": 1,
"self": 0.4919983959927663,
"children": {
"TrainerController._reset_env": {
"total": 2.541408377000039,
"count": 1,
"self": 2.541408377000039
},
"TrainerController.advance": {
"total": 378.16422042800724,
"count": 18204,
"self": 0.24246082800362956,
"children": {
"env_step": {
"total": 377.9217596000036,
"count": 18204,
"self": 257.48284076801394,
"children": {
"SubprocessEnvManager._take_step": {
"total": 120.19995324499877,
"count": 18204,
"self": 1.2417361909970168,
"children": {
"TorchPolicy.evaluate": {
"total": 118.95821705400175,
"count": 18204,
"self": 118.95821705400175
}
}
},
"workers": {
"total": 0.23896558699090065,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 380.64933840299886,
"count": 18204,
"is_parallel": true,
"self": 192.0070006120025,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0024261010000259375,
"count": 1,
"is_parallel": true,
"self": 0.0007182550000379706,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001707845999987967,
"count": 10,
"is_parallel": true,
"self": 0.001707845999987967
}
}
},
"UnityEnvironment.step": {
"total": 0.02725682200002666,
"count": 1,
"is_parallel": true,
"self": 0.00047752799997624606,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025585700001329315,
"count": 1,
"is_parallel": true,
"self": 0.00025585700001329315
},
"communicator.exchange": {
"total": 0.025220988999990368,
"count": 1,
"is_parallel": true,
"self": 0.025220988999990368
},
"steps_from_proto": {
"total": 0.001302448000046752,
"count": 1,
"is_parallel": true,
"self": 0.0002802780001047722,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010221699999419798,
"count": 10,
"is_parallel": true,
"self": 0.0010221699999419798
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 188.64233779099635,
"count": 18203,
"is_parallel": true,
"self": 7.1547850800014885,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 3.771997910995765,
"count": 18203,
"is_parallel": true,
"self": 3.771997910995765
},
"communicator.exchange": {
"total": 154.6407960699956,
"count": 18203,
"is_parallel": true,
"self": 154.6407960699956
},
"steps_from_proto": {
"total": 23.07475873000351,
"count": 18203,
"is_parallel": true,
"self": 4.446315029016887,
"children": {
"_process_rank_one_or_two_observation": {
"total": 18.628443700986622,
"count": 182030,
"is_parallel": true,
"self": 18.628443700986622
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001578669999844351,
"count": 1,
"self": 0.0001578669999844351,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 377.24410646299924,
"count": 240982,
"is_parallel": true,
"self": 3.3686634249957024,
"children": {
"process_trajectory": {
"total": 212.74214059500292,
"count": 240982,
"is_parallel": true,
"self": 212.01034879800284,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7317917970000849,
"count": 4,
"is_parallel": true,
"self": 0.7317917970000849
}
}
},
"_update_policy": {
"total": 161.13330244300062,
"count": 90,
"is_parallel": true,
"self": 37.717974063998156,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.41532837900246,
"count": 4587,
"is_parallel": true,
"self": 123.41532837900246
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08652731999995922,
"count": 1,
"self": 0.0008904779999738821,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08563684199998534,
"count": 1,
"self": 0.08563684199998534
}
}
}
}
}
}
}