thomaspalomares's picture
Notebook push
e1b3c8f verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.059851050376892,
"min": 1.059851050376892,
"max": 2.8699748516082764,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10096.1416015625,
"min": 10096.1416015625,
"max": 29391.412109375,
"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": 12.602054595947266,
"min": 0.4176887571811676,
"max": 12.602054595947266,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2457.400634765625,
"min": 81.0316162109375,
"max": 2546.294921875,
"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": 0.06621501080328873,
"min": 0.06248844531547352,
"max": 0.07629131062518961,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2648600432131549,
"min": 0.2599662370402275,
"max": 0.3637090728860166,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19856843797891746,
"min": 0.13054645665939532,
"max": 0.2773197995097029,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7942737519156698,
"min": 0.5221858266375813,
"max": 1.3865989975485147,
"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": 24.977272727272727,
"min": 3.4318181818181817,
"max": 24.977272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1099.0,
"min": 151.0,
"max": 1350.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.977272727272727,
"min": 3.4318181818181817,
"max": 24.977272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1099.0,
"min": 151.0,
"max": 1350.0,
"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": "1720794563",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [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": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720795028"
},
"total": 465.110773079,
"count": 1,
"self": 0.44139756099997385,
"children": {
"run_training.setup": {
"total": 0.060824339000021155,
"count": 1,
"self": 0.060824339000021155
},
"TrainerController.start_learning": {
"total": 464.608551179,
"count": 1,
"self": 0.5974832030070161,
"children": {
"TrainerController._reset_env": {
"total": 3.0628021980000426,
"count": 1,
"self": 3.0628021980000426
},
"TrainerController.advance": {
"total": 460.85398814199283,
"count": 18200,
"self": 0.3022069419853892,
"children": {
"env_step": {
"total": 460.55178120000744,
"count": 18200,
"self": 299.9394577790105,
"children": {
"SubprocessEnvManager._take_step": {
"total": 160.3013185039975,
"count": 18200,
"self": 1.5352400350028006,
"children": {
"TorchPolicy.evaluate": {
"total": 158.7660784689947,
"count": 18200,
"self": 158.7660784689947
}
}
},
"workers": {
"total": 0.3110049169994227,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.2484179850058,
"count": 18200,
"is_parallel": true,
"self": 233.21835906700295,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007849560000011024,
"count": 1,
"is_parallel": true,
"self": 0.003455231999851094,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0043943280001599305,
"count": 10,
"is_parallel": true,
"self": 0.0043943280001599305
}
}
},
"UnityEnvironment.step": {
"total": 0.03630658800000219,
"count": 1,
"is_parallel": true,
"self": 0.0006759609999562599,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040035900002521885,
"count": 1,
"is_parallel": true,
"self": 0.00040035900002521885
},
"communicator.exchange": {
"total": 0.033117396000022836,
"count": 1,
"is_parallel": true,
"self": 0.033117396000022836
},
"steps_from_proto": {
"total": 0.0021128719999978784,
"count": 1,
"is_parallel": true,
"self": 0.00042285800003583063,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016900139999620478,
"count": 10,
"is_parallel": true,
"self": 0.0016900139999620478
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 230.03005891800285,
"count": 18199,
"is_parallel": true,
"self": 10.333090024016883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.505105307994427,
"count": 18199,
"is_parallel": true,
"self": 5.505105307994427
},
"communicator.exchange": {
"total": 180.3700556750008,
"count": 18199,
"is_parallel": true,
"self": 180.3700556750008
},
"steps_from_proto": {
"total": 33.82180791099074,
"count": 18199,
"is_parallel": true,
"self": 6.614505884001858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.207302026988884,
"count": 181990,
"is_parallel": true,
"self": 27.207302026988884
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001800460000822568,
"count": 1,
"self": 0.0001800460000822568,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 455.05378282603306,
"count": 710599,
"is_parallel": true,
"self": 14.803217937068496,
"children": {
"process_trajectory": {
"total": 249.30977661296475,
"count": 710599,
"is_parallel": true,
"self": 248.6066282709648,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7031483419999631,
"count": 4,
"is_parallel": true,
"self": 0.7031483419999631
}
}
},
"_update_policy": {
"total": 190.9407882759998,
"count": 90,
"is_parallel": true,
"self": 61.96080015299964,
"children": {
"TorchPPOOptimizer.update": {
"total": 128.97998812300017,
"count": 4587,
"is_parallel": true,
"self": 128.97998812300017
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0940975900000467,
"count": 1,
"self": 0.0010173340000392272,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09308025600000747,
"count": 1,
"self": 0.09308025600000747
}
}
}
}
}
}
}