wywang's picture
Default parameter in the colab
15ccebe verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9855821132659912,
"min": 0.9855821132659912,
"max": 2.8701858520507812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9410.337890625,
"min": 9410.337890625,
"max": 29425.14453125,
"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": 12.659239768981934,
"min": 0.2919389605522156,
"max": 12.659239768981934,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2468.5517578125,
"min": 56.63615798950195,
"max": 2561.953125,
"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": 0.07003700276614908,
"min": 0.0652133694927804,
"max": 0.07859530760099148,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2801480110645963,
"min": 0.2608534779711216,
"max": 0.36178098419393134,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.22153131846411556,
"min": 0.09772294465516347,
"max": 0.27778221789528346,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8861252738564622,
"min": 0.3908917786206539,
"max": 1.3889110894764172,
"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": 24.795454545454547,
"min": 2.8181818181818183,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1091.0,
"min": 124.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.795454545454547,
"min": 2.8181818181818183,
"max": 25.045454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1091.0,
"min": 124.0,
"max": 1375.0,
"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": "1711511019",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1711511544"
},
"total": 525.2244645650001,
"count": 1,
"self": 0.49738490900006127,
"children": {
"run_training.setup": {
"total": 0.06072127200002342,
"count": 1,
"self": 0.06072127200002342
},
"TrainerController.start_learning": {
"total": 524.666358384,
"count": 1,
"self": 0.7487710470007869,
"children": {
"TrainerController._reset_env": {
"total": 2.9071594219999497,
"count": 1,
"self": 2.9071594219999497
},
"TrainerController.advance": {
"total": 520.9009882049992,
"count": 18199,
"self": 0.3643959819958127,
"children": {
"env_step": {
"total": 520.5365922230034,
"count": 18199,
"self": 340.6821874179809,
"children": {
"SubprocessEnvManager._take_step": {
"total": 179.48399744101425,
"count": 18199,
"self": 1.7991083010330158,
"children": {
"TorchPolicy.evaluate": {
"total": 177.68488913998124,
"count": 18199,
"self": 177.68488913998124
}
}
},
"workers": {
"total": 0.3704073640082015,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 523.0589175120002,
"count": 18199,
"is_parallel": true,
"self": 256.08952534498826,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053192459999991115,
"count": 1,
"is_parallel": true,
"self": 0.003640330000052927,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016789159999461845,
"count": 10,
"is_parallel": true,
"self": 0.0016789159999461845
}
}
},
"UnityEnvironment.step": {
"total": 0.04082080400007726,
"count": 1,
"is_parallel": true,
"self": 0.0007734630000868492,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004611939999676906,
"count": 1,
"is_parallel": true,
"self": 0.0004611939999676906
},
"communicator.exchange": {
"total": 0.03742098399993665,
"count": 1,
"is_parallel": true,
"self": 0.03742098399993665
},
"steps_from_proto": {
"total": 0.0021651630000860678,
"count": 1,
"is_parallel": true,
"self": 0.00039140500018675084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001773757999899317,
"count": 10,
"is_parallel": true,
"self": 0.001773757999899317
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 266.96939216701196,
"count": 18198,
"is_parallel": true,
"self": 12.086633386999893,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.421694078007363,
"count": 18198,
"is_parallel": true,
"self": 6.421694078007363
},
"communicator.exchange": {
"total": 207.93292066699587,
"count": 18198,
"is_parallel": true,
"self": 207.93292066699587
},
"steps_from_proto": {
"total": 40.528144035008836,
"count": 18198,
"is_parallel": true,
"self": 7.954584627989789,
"children": {
"_process_rank_one_or_two_observation": {
"total": 32.57355940701905,
"count": 181980,
"is_parallel": true,
"self": 32.57355940701905
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001450590000331431,
"count": 1,
"self": 0.0001450590000331431,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 514.0085794929566,
"count": 795612,
"is_parallel": true,
"self": 18.122359385948926,
"children": {
"process_trajectory": {
"total": 288.2795755170082,
"count": 795612,
"is_parallel": true,
"self": 287.65842847000806,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6211470470001359,
"count": 4,
"is_parallel": true,
"self": 0.6211470470001359
}
}
},
"_update_policy": {
"total": 207.60664458999952,
"count": 90,
"is_parallel": true,
"self": 58.848046102005924,
"children": {
"TorchPPOOptimizer.update": {
"total": 148.7585984879936,
"count": 4584,
"is_parallel": true,
"self": 148.7585984879936
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10929465100002744,
"count": 1,
"self": 0.0007797500002197921,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10851490099980765,
"count": 1,
"self": 0.10851490099980765
}
}
}
}
}
}
}