jojo80565's picture
First Push
39f11d3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8987107872962952,
"min": 0.8881112337112427,
"max": 2.871150255203247,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8580.890625,
"min": 8580.890625,
"max": 29403.44921875,
"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": 13.289850234985352,
"min": 0.1555943787097931,
"max": 13.289850234985352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2591.520751953125,
"min": 30.1853084564209,
"max": 2703.233154296875,
"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": 0.06841791323876903,
"min": 0.060600076212294345,
"max": 0.07431304086003365,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2736716529550761,
"min": 0.24240030484917738,
"max": 0.36939446989551883,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20341069711481824,
"min": 0.12077316105498145,
"max": 0.2883191684881846,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.813642788459273,
"min": 0.4830926442199258,
"max": 1.441595842440923,
"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": 25.454545454545453,
"min": 3.0454545454545454,
"max": 26.145454545454545,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1120.0,
"min": 134.0,
"max": 1438.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.454545454545453,
"min": 3.0454545454545454,
"max": 26.145454545454545,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1120.0,
"min": 134.0,
"max": 1438.0,
"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": "1709015739",
"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": "1709016171"
},
"total": 432.288135042,
"count": 1,
"self": 0.4313779720000639,
"children": {
"run_training.setup": {
"total": 0.052165480999974534,
"count": 1,
"self": 0.052165480999974534
},
"TrainerController.start_learning": {
"total": 431.804591589,
"count": 1,
"self": 0.5525825050132198,
"children": {
"TrainerController._reset_env": {
"total": 3.2559466980000025,
"count": 1,
"self": 3.2559466980000025
},
"TrainerController.advance": {
"total": 427.9086962359868,
"count": 18199,
"self": 0.25285774396684246,
"children": {
"env_step": {
"total": 427.65583849201994,
"count": 18199,
"self": 275.84376474102726,
"children": {
"SubprocessEnvManager._take_step": {
"total": 151.54342381400545,
"count": 18199,
"self": 1.4148202320067185,
"children": {
"TorchPolicy.evaluate": {
"total": 150.12860358199873,
"count": 18199,
"self": 150.12860358199873
}
}
},
"workers": {
"total": 0.26864993698723083,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 430.6739820919897,
"count": 18199,
"is_parallel": true,
"self": 215.13057648100335,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005823764999945524,
"count": 1,
"is_parallel": true,
"self": 0.004035304999888467,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017884600000570572,
"count": 10,
"is_parallel": true,
"self": 0.0017884600000570572
}
}
},
"UnityEnvironment.step": {
"total": 0.038162041999953544,
"count": 1,
"is_parallel": true,
"self": 0.0006315880000329344,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00042962099996657344,
"count": 1,
"is_parallel": true,
"self": 0.00042962099996657344
},
"communicator.exchange": {
"total": 0.0351865899999666,
"count": 1,
"is_parallel": true,
"self": 0.0351865899999666
},
"steps_from_proto": {
"total": 0.0019142429999874366,
"count": 1,
"is_parallel": true,
"self": 0.0003597580000587186,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001554484999928718,
"count": 10,
"is_parallel": true,
"self": 0.001554484999928718
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.54340561098638,
"count": 18198,
"is_parallel": true,
"self": 10.401126365980076,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.289701740017563,
"count": 18198,
"is_parallel": true,
"self": 5.289701740017563
},
"communicator.exchange": {
"total": 167.3484328129981,
"count": 18198,
"is_parallel": true,
"self": 167.3484328129981
},
"steps_from_proto": {
"total": 32.50414469199063,
"count": 18198,
"is_parallel": true,
"self": 5.948829942994507,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.555314748996125,
"count": 181980,
"is_parallel": true,
"self": 26.555314748996125
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.6866000073132454e-05,
"count": 1,
"self": 3.6866000073132454e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 422.63426335902693,
"count": 657305,
"is_parallel": true,
"self": 13.564004770993279,
"children": {
"process_trajectory": {
"total": 231.43392282103343,
"count": 657305,
"is_parallel": true,
"self": 230.97239649403366,
"children": {
"RLTrainer._checkpoint": {
"total": 0.46152632699977403,
"count": 4,
"is_parallel": true,
"self": 0.46152632699977403
}
}
},
"_update_policy": {
"total": 177.63633576700022,
"count": 90,
"is_parallel": true,
"self": 53.04720509499873,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.58913067200149,
"count": 4587,
"is_parallel": true,
"self": 124.58913067200149
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.08732928399990669,
"count": 1,
"self": 0.0009647100000620412,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08636457399984465,
"count": 1,
"self": 0.08636457399984465
}
}
}
}
}
}
}