{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bayesian-inference-with-anchored-ensembles-of","title":"Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Exploration in Reinforcement Learning","arxiv_id":"1805.11324","date":"2018-05-29","proceeding":null,"authors":["Tim Pearce","Nicolas Anastassacos","Mohamed Zaki","Andy Neely"],"abstract":"The use of ensembles of neural networks (NNs) for the quantification of\npredictive uncertainty is widespread. However, the current justification is\nintuitive rather than analytical. This work proposes one minor modification to\nthe normal ensembling methodology, which we prove allows the ensemble to\nperform Bayesian inference, hence converging to the corresponding Gaussian\nProcess as both the total number of NNs, and the size of each, tend to\ninfinity. This working paper provides early-stage results in a reinforcement\nlearning setting, analysing the practicality of the technique for an ensemble\nof small, finite number. Using the uncertainty estimates produced by anchored\nensembles to govern the exploration-exploitation process results in steadier,\nmore stable learning.","url_abs":"http://arxiv.org/abs/1805.11324v3","url_pdf":"http://arxiv.org/pdf/1805.11324v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bayesian-inference-with-anchored-ensembles-of","repo_url":"https://github.com/TeaPearce/Anchored_Ens_RL_Explore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"bayesian-inference-with-anchored-ensembles-of","repo_url":"https://github.com/TeaPearce/RL_Cart_Pole_Speed_Run","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.11324","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}