Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry (Extended Abstract)
Abstract
Agents operating in the real world must cope with the fact that time passes while they plan. In some cases, such as under tight deadlines, the only way for such an agent to achieve its goal is to execute an action before a complete plan has been found. This problem is called Concurrent Planning and Execution (CoPE). Previous work on CoPE relied on a value function that assumes search will finish before actions are executed, causing the agent to be overly pessimistic in many situations. In this paper, we define a new value function that takes into account the agent's ability to dispatch actions incrementally. This allows us to devise a much simpler algorithm for concurrent planning and execution. An experimental evaluation on problems with time pressure shows that the new method significantly outperforms the previous state-of-the-art.
Cite
Text
Wiese et al. "Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/943Markdown
[Wiese et al. "Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/wiese2024ijcai-efficient/) doi:10.24963/ijcai.2024/943BibTeX
@inproceedings{wiese2024ijcai-efficient,
title = {{Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry (Extended Abstract)}},
author = {Wiese, Jonas Gregor and Wimmer, Lisa and Papamarkou, Theodore and Bischl, Bernd and Günnemann, Stephan and Rügamer, David},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {8466-8470},
doi = {10.24963/ijcai.2024/943},
url = {https://mlanthology.org/ijcai/2024/wiese2024ijcai-efficient/}
}