{"url":"/method/bayesian-rex","slug":"bayesian-rex","name":"Bayesian REX","full_name":"Bayesian Reward Extrapolation","full_name_withheld":false,"description_markdown":"**Bayesian Reward Extrapolation** is a Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","paper":"/paper/safe-imitation-learning-via-fast-bayesian","first_author":"Daniel S. Brown","n_authors":4,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/safe-imitation-learning-via-fast-bayesian"},"source":{"url":"https://arxiv.org/abs/2002.09089v4","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Reinforcement Learning","area_id":"reinforcement-learning","collection":"Bayesian Reinforcement Learning","url":"/methods/category/bayesian-reinforcement-learning","pwc_aliases":[]}],"n_papers_tagged":1,"archive_num_papers":1,"papers_newest_first":[{"paper":"/paper/safe-imitation-learning-via-fast-bayesian","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","date":"2020-02-21","arxiv_id":"2002.09089","n_code_links":1,"syntology":{"ran":5,"of":10,"unverified":5,"pointer_only":0}}],"papers_shown":1,"tasks":[{"task":"/task/atari-games","name":"Atari Games","papers":1},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":1},{"task":"/task/imitation-learning","name":"Imitation Learning","papers":1}],"tasks_shown":3,"n_tasks":3,"usage_by_year":[{"year":"2020","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/bayesian-rex"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}