LiamZ0302's picture
First Try
d4a5454
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0223031044006348,
"min": 0.9678168892860413,
"max": 2.866833448410034,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9794.6865234375,
"min": 9379.11328125,
"max": 29453.845703125,
"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": 12.041596412658691,
"min": 0.36007076501846313,
"max": 12.041596412658691,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2348.111328125,
"min": 69.85372924804688,
"max": 2439.30224609375,
"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": 0.06982636179400645,
"min": 0.0661204807641779,
"max": 0.07301201968988535,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2793054471760258,
"min": 0.2655471568595043,
"max": 0.3650600984494268,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18654464937600437,
"min": 0.15895722623841435,
"max": 0.2802397803056474,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7461785975040175,
"min": 0.6358289049536574,
"max": 1.2994595132037705,
"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": 23.886363636363637,
"min": 3.9318181818181817,
"max": 23.963636363636365,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1051.0,
"min": 173.0,
"max": 1318.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.886363636363637,
"min": 3.9318181818181817,
"max": 23.963636363636365,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1051.0,
"min": 173.0,
"max": 1318.0,
"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": "1682419911",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1682420382"
},
"total": 470.30893997000004,
"count": 1,
"self": 0.38467252700002064,
"children": {
"run_training.setup": {
"total": 0.11007555800000546,
"count": 1,
"self": 0.11007555800000546
},
"TrainerController.start_learning": {
"total": 469.814191885,
"count": 1,
"self": 0.5852197389996832,
"children": {
"TrainerController._reset_env": {
"total": 3.7663232389999735,
"count": 1,
"self": 3.7663232389999735
},
"TrainerController.advance": {
"total": 465.30889277200026,
"count": 18203,
"self": 0.2769848429950912,
"children": {
"env_step": {
"total": 465.0319079290052,
"count": 18203,
"self": 337.3769342830064,
"children": {
"SubprocessEnvManager._take_step": {
"total": 127.37149204099757,
"count": 18203,
"self": 1.8367081919915904,
"children": {
"TorchPolicy.evaluate": {
"total": 125.53478384900598,
"count": 18203,
"self": 125.53478384900598
}
}
},
"workers": {
"total": 0.28348160500121367,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 468.27274372299985,
"count": 18203,
"is_parallel": true,
"self": 215.98717588399927,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005933222999999543,
"count": 1,
"is_parallel": true,
"self": 0.00419517000000269,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001738052999996853,
"count": 10,
"is_parallel": true,
"self": 0.001738052999996853
}
}
},
"UnityEnvironment.step": {
"total": 0.03799717300000793,
"count": 1,
"is_parallel": true,
"self": 0.0005371240000044963,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00035731499997382343,
"count": 1,
"is_parallel": true,
"self": 0.00035731499997382343
},
"communicator.exchange": {
"total": 0.0351634049999916,
"count": 1,
"is_parallel": true,
"self": 0.0351634049999916
},
"steps_from_proto": {
"total": 0.0019393290000380148,
"count": 1,
"is_parallel": true,
"self": 0.00035861300005990415,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015807159999781106,
"count": 10,
"is_parallel": true,
"self": 0.0015807159999781106
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 252.28556783900058,
"count": 18202,
"is_parallel": true,
"self": 10.030513832997883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6365572209934385,
"count": 18202,
"is_parallel": true,
"self": 5.6365572209934385
},
"communicator.exchange": {
"total": 203.25191671200366,
"count": 18202,
"is_parallel": true,
"self": 203.25191671200366
},
"steps_from_proto": {
"total": 33.36658007300559,
"count": 18202,
"is_parallel": true,
"self": 6.69381088902594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.672769183979653,
"count": 182020,
"is_parallel": true,
"self": 26.672769183979653
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00011436500005856942,
"count": 1,
"self": 0.00011436500005856942,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 461.49686545898027,
"count": 410926,
"is_parallel": true,
"self": 10.74089848299269,
"children": {
"process_trajectory": {
"total": 258.32622360598805,
"count": 410926,
"is_parallel": true,
"self": 257.553233249988,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7729903560000366,
"count": 4,
"is_parallel": true,
"self": 0.7729903560000366
}
}
},
"_update_policy": {
"total": 192.42974336999953,
"count": 90,
"is_parallel": true,
"self": 66.64968811899263,
"children": {
"TorchPPOOptimizer.update": {
"total": 125.7800552510069,
"count": 4587,
"is_parallel": true,
"self": 125.7800552510069
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.15364177000003565,
"count": 1,
"self": 0.0009727550000206975,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15266901500001495,
"count": 1,
"self": 0.15266901500001495
}
}
}
}
}
}
}