{"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/combined-reinforcement-learning-via-abstract","title":"Combined Reinforcement Learning via Abstract Representations","arxiv_id":"1809.04506","date":"2018-09-12","proceeding":null,"authors":["Vincent François-Lavet","Yoshua Bengio","Doina Precup","Joelle Pineau"],"abstract":"In the quest for efficient and robust reinforcement learning methods, both\nmodel-free and model-based approaches offer advantages. In this paper we\npropose a new way of explicitly bridging both approaches via a shared\nlow-dimensional learned encoding of the environment, meant to capture\nsummarizing abstractions. We show that the modularity brought by this approach\nleads to good generalization while being computationally efficient, with\nplanning happening in a smaller latent state space. In addition, this approach\nrecovers a sufficient low-dimensional representation of the environment, which\nopens up new strategies for interpretable AI, exploration and transfer\nlearning.","url_abs":"http://arxiv.org/abs/1809.04506v2","url_pdf":"http://arxiv.org/pdf/1809.04506v2.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":"combined-reinforcement-learning-via-abstract","repo_url":"https://github.com/VinF/deer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.04506","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}