{"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/learning-and-policy-search-in-stochastic","title":"Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks","arxiv_id":"1605.07127","date":"2016-05-23","proceeding":null,"authors":["Stefan Depeweg","José Miguel Hernández-Lobato","Finale Doshi-Velez","Steffen Udluft"],"abstract":"We present an algorithm for model-based reinforcement learning that combines\nBayesian neural networks (BNNs) with random roll-outs and stochastic\noptimization for policy learning. The BNNs are trained by minimizing\n$\\alpha$-divergences, allowing us to capture complicated statistical patterns\nin the transition dynamics, e.g. multi-modality and heteroskedasticity, which\nare usually missed by other common modeling approaches. We illustrate the\nperformance of our method by solving a challenging benchmark where model-based\napproaches usually fail and by obtaining promising results in a real-world\nscenario for controlling a gas turbine.","url_abs":"http://arxiv.org/abs/1605.07127v3","url_pdf":"http://arxiv.org/pdf/1605.07127v3.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":"learning-and-policy-search-in-stochastic","repo_url":"https://github.com/siemens/industrialbenchmark","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-and-policy-search-in-stochastic","repo_url":"https://github.com/siemens/policy_search_bb-alpha","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1605.07127","atlas_url":"https://app.syntology.ai/?focus=1605.07127","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}