abdel1311's picture
First Push
a5de7e3
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9967924356460571,
"min": 0.9967924356460571,
"max": 2.865035057067871,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9528.3388671875,
"min": 9528.3388671875,
"max": 29372.33984375,
"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": 12.715271949768066,
"min": 0.3313049376010895,
"max": 12.715271949768066,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2479.47802734375,
"min": 64.27315521240234,
"max": 2550.041259765625,
"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": 0.07320930998692204,
"min": 0.06210693396408483,
"max": 0.07571863200849062,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2928372399476882,
"min": 0.25995192568356573,
"max": 0.3785931600424531,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18856381391193353,
"min": 0.1370101491703798,
"max": 0.28629302854339284,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7542552556477341,
"min": 0.5480405966815192,
"max": 1.3470667109769934,
"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": 25.863636363636363,
"min": 3.5681818181818183,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1138.0,
"min": 157.0,
"max": 1370.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.863636363636363,
"min": 3.5681818181818183,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1138.0,
"min": 157.0,
"max": 1370.0,
"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": "1703618425",
"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=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.2+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1703618863"
},
"total": 437.4925646679999,
"count": 1,
"self": 0.43986602499990113,
"children": {
"run_training.setup": {
"total": 0.07449827400000686,
"count": 1,
"self": 0.07449827400000686
},
"TrainerController.start_learning": {
"total": 436.978200369,
"count": 1,
"self": 0.5164444759866456,
"children": {
"TrainerController._reset_env": {
"total": 3.4738754590000553,
"count": 1,
"self": 3.4738754590000553
},
"TrainerController.advance": {
"total": 432.90123253901334,
"count": 18200,
"self": 0.2610262760115347,
"children": {
"env_step": {
"total": 432.6402062630018,
"count": 18200,
"self": 283.80267449599955,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.5687459270099,
"count": 18200,
"self": 1.420722707007826,
"children": {
"TorchPolicy.evaluate": {
"total": 147.14802322000207,
"count": 18200,
"self": 147.14802322000207
}
}
},
"workers": {
"total": 0.26878583999234706,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 435.8381470049982,
"count": 18200,
"is_parallel": true,
"self": 215.5524808079922,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007287533999942752,
"count": 1,
"is_parallel": true,
"self": 0.004112784000085412,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0031747499998573403,
"count": 10,
"is_parallel": true,
"self": 0.0031747499998573403
}
}
},
"UnityEnvironment.step": {
"total": 0.0390912399999479,
"count": 1,
"is_parallel": true,
"self": 0.0007224559999485791,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00044112299997323134,
"count": 1,
"is_parallel": true,
"self": 0.00044112299997323134
},
"communicator.exchange": {
"total": 0.03568195699995158,
"count": 1,
"is_parallel": true,
"self": 0.03568195699995158
},
"steps_from_proto": {
"total": 0.002245704000074511,
"count": 1,
"is_parallel": true,
"self": 0.0004220430000714259,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001823661000003085,
"count": 10,
"is_parallel": true,
"self": 0.001823661000003085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.28566619700598,
"count": 18199,
"is_parallel": true,
"self": 10.536959484990575,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.26588742000763,
"count": 18199,
"is_parallel": true,
"self": 5.26588742000763
},
"communicator.exchange": {
"total": 171.36824159101832,
"count": 18199,
"is_parallel": true,
"self": 171.36824159101832
},
"steps_from_proto": {
"total": 33.11457770098946,
"count": 18199,
"is_parallel": true,
"self": 6.191597572938576,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.92298012805088,
"count": 181990,
"is_parallel": true,
"self": 26.92298012805088
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012648799997805327,
"count": 1,
"self": 0.00012648799997805327,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 427.5417940120202,
"count": 657563,
"is_parallel": true,
"self": 14.094112212997402,
"children": {
"process_trajectory": {
"total": 236.05730137102194,
"count": 657563,
"is_parallel": true,
"self": 235.57813608402193,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4791652870000007,
"count": 4,
"is_parallel": true,
"self": 0.4791652870000007
}
}
},
"_update_policy": {
"total": 177.39038042800087,
"count": 90,
"is_parallel": true,
"self": 55.18145822199688,
"children": {
"TorchPPOOptimizer.update": {
"total": 122.20892220600399,
"count": 4587,
"is_parallel": true,
"self": 122.20892220600399
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0865214069999638,
"count": 1,
"self": 0.0009579639997809863,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08556344300018282,
"count": 1,
"self": 0.08556344300018282
}
}
}
}
}
}
}