B-ramB's picture
First Push
9b00562 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6185718178749084,
"min": 0.6185718178749084,
"max": 2.85929274559021,
"count": 50
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 5933.3408203125,
"min": 5933.3408203125,
"max": 29187.66015625,
"count": 50
},
"SnowballTarget.Step.mean": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Step.sum": {
"value": 499976.0,
"min": 9952.0,
"max": 499976.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.875882148742676,
"min": 0.4311749041080475,
"max": 13.875882148742676,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2844.555908203125,
"min": 83.64793395996094,
"max": 2844.555908203125,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06667108432898827,
"min": 0.060153363646153875,
"max": 0.07903943160735984,
"count": 50
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.33335542164494136,
"min": 0.2406134545846155,
"max": 0.3729976419434773,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1786470852646173,
"min": 0.11377847427388142,
"max": 0.2872975215169729,
"count": 50
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8932354263230866,
"min": 0.4551138970955257,
"max": 1.3837955331101137,
"count": 50
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 3.0528989824000028e-06,
"min": 3.0528989824000028e-06,
"max": 0.00029675280108239997,
"count": 50
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.5264494912000015e-05,
"min": 1.5264494912000015e-05,
"max": 0.001454064015312,
"count": 50
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10101760000000001,
"min": 0.10101760000000001,
"max": 0.19891759999999997,
"count": 50
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5050880000000001,
"min": 0.41199040000000003,
"max": 0.984688,
"count": 50
},
"SnowballTarget.Policy.Beta.mean": {
"value": 6.0778240000000044e-05,
"min": 6.0778240000000044e-05,
"max": 0.00494598824,
"count": 50
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0003038912000000002,
"min": 0.0003038912000000002,
"max": 0.0242359312,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 50
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 27.054545454545455,
"min": 3.659090909090909,
"max": 27.363636363636363,
"count": 50
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1488.0,
"min": 161.0,
"max": 1488.0,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 27.054545454545455,
"min": 3.659090909090909,
"max": 27.363636363636363,
"count": 50
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1488.0,
"min": 161.0,
"max": 1488.0,
"count": 50
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 50
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1747481421",
"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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747482486"
},
"total": 1065.361272687,
"count": 1,
"self": 0.7824692920003145,
"children": {
"run_training.setup": {
"total": 0.022493344999929832,
"count": 1,
"self": 0.022493344999929832
},
"TrainerController.start_learning": {
"total": 1064.5563100499999,
"count": 1,
"self": 0.8518359309871357,
"children": {
"TrainerController._reset_env": {
"total": 3.1107617220000066,
"count": 1,
"self": 3.1107617220000066
},
"TrainerController.advance": {
"total": 1060.467006368013,
"count": 45464,
"self": 0.9344915320257314,
"children": {
"env_step": {
"total": 752.3636211069839,
"count": 45464,
"self": 575.1322708600181,
"children": {
"SubprocessEnvManager._take_step": {
"total": 176.71723226198628,
"count": 45464,
"self": 3.173365624997132,
"children": {
"TorchPolicy.evaluate": {
"total": 173.54386663698915,
"count": 45464,
"self": 173.54386663698915
}
}
},
"workers": {
"total": 0.5141179849795208,
"count": 45464,
"self": 0.0,
"children": {
"worker_root": {
"total": 1061.1664498280047,
"count": 45464,
"is_parallel": true,
"self": 556.7150788140112,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005293461000064781,
"count": 1,
"is_parallel": true,
"self": 0.00392517200009479,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001368288999969991,
"count": 10,
"is_parallel": true,
"self": 0.001368288999969991
}
}
},
"UnityEnvironment.step": {
"total": 0.0353813839999475,
"count": 1,
"is_parallel": true,
"self": 0.000541385999895283,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003835410000192496,
"count": 1,
"is_parallel": true,
"self": 0.0003835410000192496
},
"communicator.exchange": {
"total": 0.032493631000079404,
"count": 1,
"is_parallel": true,
"self": 0.032493631000079404
},
"steps_from_proto": {
"total": 0.0019628259999535658,
"count": 1,
"is_parallel": true,
"self": 0.00038504299993746827,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015777830000160975,
"count": 10,
"is_parallel": true,
"self": 0.0015777830000160975
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 504.4513710139935,
"count": 45463,
"is_parallel": true,
"self": 24.10411650003516,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 13.750034730988773,
"count": 45463,
"is_parallel": true,
"self": 13.750034730988773
},
"communicator.exchange": {
"total": 386.6319018649974,
"count": 45463,
"is_parallel": true,
"self": 386.6319018649974
},
"steps_from_proto": {
"total": 79.96531791797213,
"count": 45463,
"is_parallel": true,
"self": 14.232640022902046,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.73267789507008,
"count": 454630,
"is_parallel": true,
"self": 65.73267789507008
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 307.16889372900334,
"count": 45464,
"self": 1.0967006580218595,
"children": {
"process_trajectory": {
"total": 68.45266550498172,
"count": 45464,
"self": 67.4365838659819,
"children": {
"RLTrainer._checkpoint": {
"total": 1.0160816389998217,
"count": 10,
"self": 1.0160816389998217
}
}
},
"_update_policy": {
"total": 237.61952756599976,
"count": 227,
"self": 98.99149686600754,
"children": {
"TorchPPOOptimizer.update": {
"total": 138.62803069999222,
"count": 11574,
"self": 138.62803069999222
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1939998785237549e-06,
"count": 1,
"self": 1.1939998785237549e-06
},
"TrainerController._save_models": {
"total": 0.12670483499982765,
"count": 1,
"self": 0.0010369509998326976,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12566788399999496,
"count": 1,
"self": 0.12566788399999496
}
}
}
}
}
}
}