dbaibak's picture
Adjested parapmeters
eff6950
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.6636300086975098,
"min": 0.5337280631065369,
"max": 2.8739378452301025,
"count": 100
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6321.7392578125,
"min": 5347.52734375,
"max": 29431.998046875,
"count": 100
},
"SnowballTarget.Step.mean": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Step.sum": {
"value": 999952.0,
"min": 9952.0,
"max": 999952.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.78328800201416,
"min": 0.34302350878715515,
"max": 13.88427734375,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2687.7412109375,
"min": 66.54656219482422,
"max": 2840.37890625,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 100
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06911364505011829,
"min": 0.062036949945356946,
"max": 0.0756221567192423,
"count": 100
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27645458020047314,
"min": 0.2535717716876755,
"max": 0.37595457388019626,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17325608344639049,
"min": 0.11902412774301518,
"max": 0.2785312884695389,
"count": 100
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.6930243337855619,
"min": 0.47609651097206074,
"max": 1.3926564423476946,
"count": 100
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 4.58899541200001e-07,
"min": 4.58899541200001e-07,
"max": 9.94588005412e-05,
"count": 100
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 1.835598164800004e-06,
"min": 1.835598164800004e-06,
"max": 0.000492344007656,
"count": 100
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10045880000000001,
"min": 0.10045880000000001,
"max": 0.19945880000000002,
"count": 100
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.40183520000000006,
"min": 0.40183520000000006,
"max": 0.9923440000000001,
"count": 100
},
"SnowballTarget.Policy.Beta.mean": {
"value": 3.289412000000005e-05,
"min": 3.289412000000005e-05,
"max": 0.004972994119999999,
"count": 100
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0001315764800000002,
"min": 0.0001315764800000002,
"max": 0.024617965600000007,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.755555555555556,
"min": 3.1136363636363638,
"max": 27.704545454545453,
"count": 100
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1204.0,
"min": 137.0,
"max": 1504.0,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.755555555555556,
"min": 3.1136363636363638,
"max": 27.704545454545453,
"count": 100
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1204.0,
"min": 137.0,
"max": 1504.0,
"count": 100
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 100
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1673779591",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1673782190"
},
"total": 2598.9647789719997,
"count": 1,
"self": 0.4438332649997392,
"children": {
"run_training.setup": {
"total": 0.11994735899997977,
"count": 1,
"self": 0.11994735899997977
},
"TrainerController.start_learning": {
"total": 2598.400998348,
"count": 1,
"self": 2.883152758980941,
"children": {
"TrainerController._reset_env": {
"total": 9.222959835999973,
"count": 1,
"self": 9.222959835999973
},
"TrainerController.advance": {
"total": 2586.156709369019,
"count": 90939,
"self": 1.633727324049687,
"children": {
"env_step": {
"total": 2584.5229820449695,
"count": 90939,
"self": 1779.743487822972,
"children": {
"SubprocessEnvManager._take_step": {
"total": 803.1892425090267,
"count": 90939,
"self": 7.924630220050744,
"children": {
"TorchPolicy.evaluate": {
"total": 795.264612288976,
"count": 90939,
"self": 181.09360327693207,
"children": {
"TorchPolicy.sample_actions": {
"total": 614.1710090120439,
"count": 90939,
"self": 614.1710090120439
}
}
}
}
},
"workers": {
"total": 1.5902517129709395,
"count": 90939,
"self": 0.0,
"children": {
"worker_root": {
"total": 2591.4573665610883,
"count": 90939,
"is_parallel": true,
"self": 1377.894624277109,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00678140299999086,
"count": 1,
"is_parallel": true,
"self": 0.004182981999747426,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002598421000243434,
"count": 10,
"is_parallel": true,
"self": 0.002598421000243434
}
}
},
"UnityEnvironment.step": {
"total": 0.03915325600007691,
"count": 1,
"is_parallel": true,
"self": 0.0005517340000551485,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031737799997699767,
"count": 1,
"is_parallel": true,
"self": 0.00031737799997699767
},
"communicator.exchange": {
"total": 0.03634834399997544,
"count": 1,
"is_parallel": true,
"self": 0.03634834399997544
},
"steps_from_proto": {
"total": 0.001935800000069321,
"count": 1,
"is_parallel": true,
"self": 0.0004421310002271639,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001493668999842157,
"count": 10,
"is_parallel": true,
"self": 0.001493668999842157
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1213.5627422839793,
"count": 90938,
"is_parallel": true,
"self": 47.008813884028996,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.262252546976015,
"count": 90938,
"is_parallel": true,
"self": 28.262252546976015
},
"communicator.exchange": {
"total": 963.8851754429767,
"count": 90938,
"is_parallel": true,
"self": 963.8851754429767
},
"steps_from_proto": {
"total": 174.40650040999765,
"count": 90938,
"is_parallel": true,
"self": 38.57970606715844,
"children": {
"_process_rank_one_or_two_observation": {
"total": 135.8267943428392,
"count": 909380,
"is_parallel": true,
"self": 135.8267943428392
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.1496999731170945e-05,
"count": 1,
"self": 5.1496999731170945e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 2568.7871171399424,
"count": 1841208,
"is_parallel": true,
"self": 53.71657861903486,
"children": {
"process_trajectory": {
"total": 1313.6175366289085,
"count": 1841208,
"is_parallel": true,
"self": 1309.528037003909,
"children": {
"RLTrainer._checkpoint": {
"total": 4.089499624999576,
"count": 20,
"is_parallel": true,
"self": 4.089499624999576
}
}
},
"_update_policy": {
"total": 1201.453001891999,
"count": 454,
"is_parallel": true,
"self": 358.5126461370397,
"children": {
"TorchPPOOptimizer.update": {
"total": 842.9403557549593,
"count": 38585,
"is_parallel": true,
"self": 842.9403557549593
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13812488700023096,
"count": 1,
"self": 0.0008637990003990126,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13726108799983194,
"count": 1,
"self": 0.13726108799983194
}
}
}
}
}
}
}