mlewand's picture
First model
898c727
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0129822492599487,
"min": 1.0022320747375488,
"max": 2.865532398223877,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9671.955078125,
"min": 9671.955078125,
"max": 29377.4375,
"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": 1.3132888078689575,
"min": 0.17706429958343506,
"max": 1.3450658321380615,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 256.09130859375,
"min": 34.3504753112793,
"max": 271.1630554199219,
"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": 0.14241242902329865,
"min": 0.13410936508270085,
"max": 0.14653003608242107,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.5696497160931946,
"min": 0.538872012877797,
"max": 0.7237184906841909,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.09708104625472105,
"min": 0.05030535016107482,
"max": 0.114962305718412,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.3883241850188842,
"min": 0.20122140064429928,
"max": 0.566489233964068,
"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": 0.0013851600382799997,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.102694,
"min": 0.102694,
"max": 0.197294,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.410776,
"min": 0.410776,
"max": 0.9617200000000001,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.00014443060000000012,
"min": 0.00014443060000000012,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000005,
"min": 0.0005777224000000005,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 26.181818181818183,
"min": 3.7954545454545454,
"max": 26.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1152.0,
"min": 167.0,
"max": 1435.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.181818181818183,
"min": 3.7954545454545454,
"max": 26.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1152.0,
"min": 167.0,
"max": 1435.0,
"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": "1677013562",
"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": "1677014148"
},
"total": 586.602671994,
"count": 1,
"self": 0.4396538910001482,
"children": {
"run_training.setup": {
"total": 0.11225277899995945,
"count": 1,
"self": 0.11225277899995945
},
"TrainerController.start_learning": {
"total": 586.0507653239999,
"count": 1,
"self": 0.5304560569983323,
"children": {
"TrainerController._reset_env": {
"total": 9.362778404999972,
"count": 1,
"self": 9.362778404999972
},
"TrainerController.advance": {
"total": 576.0232007970018,
"count": 18203,
"self": 0.269900310994899,
"children": {
"env_step": {
"total": 575.7533004860069,
"count": 18203,
"self": 449.01168591201593,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.4798279329977,
"count": 18203,
"self": 1.614710467996531,
"children": {
"TorchPolicy.evaluate": {
"total": 124.86511746500116,
"count": 18203,
"self": 25.687336073995994,
"children": {
"TorchPolicy.sample_actions": {
"total": 99.17778139100517,
"count": 18203,
"self": 99.17778139100517
}
}
}
}
},
"workers": {
"total": 0.26178664099325033,
"count": 18203,
"self": 0.0,
"children": {
"worker_root": {
"total": 584.5668244570005,
"count": 18203,
"is_parallel": true,
"self": 350.9664639509948,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00581876899997269,
"count": 1,
"is_parallel": true,
"self": 0.00333069899994598,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0024880700000267097,
"count": 10,
"is_parallel": true,
"self": 0.0024880700000267097
}
}
},
"UnityEnvironment.step": {
"total": 0.04523794100003897,
"count": 1,
"is_parallel": true,
"self": 0.0004607200000350531,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029067600002008476,
"count": 1,
"is_parallel": true,
"self": 0.00029067600002008476
},
"communicator.exchange": {
"total": 0.042946053999969536,
"count": 1,
"is_parallel": true,
"self": 0.042946053999969536
},
"steps_from_proto": {
"total": 0.001540491000014299,
"count": 1,
"is_parallel": true,
"self": 0.00038756999987299423,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0011529210001413048,
"count": 10,
"is_parallel": true,
"self": 0.0011529210001413048
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 233.6003605060057,
"count": 18202,
"is_parallel": true,
"self": 9.613930197999991,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.116165963004676,
"count": 18202,
"is_parallel": true,
"self": 5.116165963004676
},
"communicator.exchange": {
"total": 187.67847348999527,
"count": 18202,
"is_parallel": true,
"self": 187.67847348999527
},
"steps_from_proto": {
"total": 31.191790855005763,
"count": 18202,
"is_parallel": true,
"self": 6.807972498996492,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.38381835600927,
"count": 182020,
"is_parallel": true,
"self": 24.38381835600927
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00010305599994353543,
"count": 1,
"self": 0.00010305599994353543,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 572.324506380019,
"count": 402859,
"is_parallel": true,
"self": 10.60138877302768,
"children": {
"process_trajectory": {
"total": 255.42190214799143,
"count": 402859,
"is_parallel": true,
"self": 253.77724548799142,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6446566600000097,
"count": 4,
"is_parallel": true,
"self": 1.6446566600000097
}
}
},
"_update_policy": {
"total": 306.3012154589999,
"count": 90,
"is_parallel": true,
"self": 57.340755418997105,
"children": {
"TorchPPOOptimizer.update": {
"total": 248.96046004000277,
"count": 18354,
"is_parallel": true,
"self": 248.96046004000277
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1342270089999147,
"count": 1,
"self": 0.0010452849999182945,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1331817239999964,
"count": 1,
"self": 0.1331817239999964
}
}
}
}
}
}
}