javiervela's picture
First training of SnowballTarget
ce67c71
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8047587275505066,
"min": 0.8047587275505066,
"max": 2.844916343688965,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7781.2119140625,
"min": 7781.2119140625,
"max": 29134.7890625,
"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": 11.816329002380371,
"min": 0.3686668276786804,
"max": 11.816329002380371,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2304.18408203125,
"min": 71.5213623046875,
"max": 2398.43115234375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06831586426044084,
"min": 0.06234255140265234,
"max": 0.0762028780719037,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27326345704176336,
"min": 0.2572842669883268,
"max": 0.38101439035951856,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1758270290698491,
"min": 0.11047851242577,
"max": 0.27533148258340123,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7033081162793964,
"min": 0.44191404970308,
"max": 1.3175450665693658,
"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": 23.545454545454547,
"min": 3.090909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1036.0,
"min": 136.0,
"max": 1281.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.545454545454547,
"min": 3.090909090909091,
"max": 23.545454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1036.0,
"min": 136.0,
"max": 1281.0,
"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": "1674759257",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "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": "1674759704"
},
"total": 446.73370976100006,
"count": 1,
"self": 0.7160155540000801,
"children": {
"run_training.setup": {
"total": 0.10207663099998854,
"count": 1,
"self": 0.10207663099998854
},
"TrainerController.start_learning": {
"total": 445.915617576,
"count": 1,
"self": 0.580501232991196,
"children": {
"TrainerController._reset_env": {
"total": 9.416779936000012,
"count": 1,
"self": 9.416779936000012
},
"TrainerController.advance": {
"total": 435.7197957920088,
"count": 18223,
"self": 0.30650851600984197,
"children": {
"env_step": {
"total": 435.413287275999,
"count": 18223,
"self": 285.16918579699336,
"children": {
"SubprocessEnvManager._take_step": {
"total": 149.9474767600039,
"count": 18223,
"self": 1.522381588008102,
"children": {
"TorchPolicy.evaluate": {
"total": 148.4250951719958,
"count": 18223,
"self": 35.602587510996045,
"children": {
"TorchPolicy.sample_actions": {
"total": 112.82250766099975,
"count": 18223,
"self": 112.82250766099975
}
}
}
}
},
"workers": {
"total": 0.29662471900172704,
"count": 18223,
"self": 0.0,
"children": {
"worker_root": {
"total": 444.4526538550004,
"count": 18223,
"is_parallel": true,
"self": 212.01011736099832,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0057125299999825074,
"count": 1,
"is_parallel": true,
"self": 0.0032123979997891183,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002500132000193389,
"count": 10,
"is_parallel": true,
"self": 0.002500132000193389
}
}
},
"UnityEnvironment.step": {
"total": 0.03982694400002629,
"count": 1,
"is_parallel": true,
"self": 0.0006353960000069492,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00039621700000225246,
"count": 1,
"is_parallel": true,
"self": 0.00039621700000225246
},
"communicator.exchange": {
"total": 0.03692699599997695,
"count": 1,
"is_parallel": true,
"self": 0.03692699599997695
},
"steps_from_proto": {
"total": 0.0018683350000401333,
"count": 1,
"is_parallel": true,
"self": 0.0004510130000880963,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001417321999952037,
"count": 10,
"is_parallel": true,
"self": 0.001417321999952037
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 232.44253649400207,
"count": 18222,
"is_parallel": true,
"self": 8.584995219995221,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.175450551002882,
"count": 18222,
"is_parallel": true,
"self": 5.175450551002882
},
"communicator.exchange": {
"total": 187.33626103000677,
"count": 18222,
"is_parallel": true,
"self": 187.33626103000677
},
"steps_from_proto": {
"total": 31.3458296929972,
"count": 18222,
"is_parallel": true,
"self": 7.066802653000934,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.279027039996265,
"count": 182220,
"is_parallel": true,
"self": 24.279027039996265
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.1517999989082455e-05,
"count": 1,
"self": 4.1517999989082455e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 432.7090723020058,
"count": 365757,
"is_parallel": true,
"self": 9.333889902044007,
"children": {
"process_trajectory": {
"total": 250.0770053869611,
"count": 365757,
"is_parallel": true,
"self": 248.97290215096132,
"children": {
"RLTrainer._checkpoint": {
"total": 1.104103235999787,
"count": 4,
"is_parallel": true,
"self": 1.104103235999787
}
}
},
"_update_policy": {
"total": 173.29817701300067,
"count": 90,
"is_parallel": true,
"self": 42.3191218649996,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.97905514800107,
"count": 4587,
"is_parallel": true,
"self": 130.97905514800107
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.19849909699996715,
"count": 1,
"self": 0.0010917869999502727,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19740731000001688,
"count": 1,
"self": 0.19740731000001688
}
}
}
}
}
}
}