{"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/the-dreaming-variational-autoencoder-for","title":"The Dreaming Variational Autoencoder for Reinforcement Learning Environments","arxiv_id":"1810.01112","date":"2018-10-02","proceeding":null,"authors":["Per-Arne Andersen","Morten Goodwin","Ole-Christoffer Granmo"],"abstract":"Reinforcement learning has shown great potential in generalizing over raw\nsensory data using only a single neural network for value optimization. There\nare several challenges in the current state-of-the-art reinforcement learning\nalgorithms that prevent them from converging towards the global optima. It is\nlikely that the solution to these problems lies in short- and long-term\nplanning, exploration and memory management for reinforcement learning\nalgorithms. Games are often used to benchmark reinforcement learning algorithms\nas they provide a flexible, reproducible, and easy to control environment.\nRegardless, few games feature a state-space where results in exploration,\nmemory, and planning are easily perceived. This paper presents The Dreaming\nVariational Autoencoder (DVAE), a neural network based generative modeling\narchitecture for exploration in environments with sparse feedback. We further\npresent Deep Maze, a novel and flexible maze engine that challenges DVAE in\npartial and fully-observable state-spaces, long-horizon tasks, and\ndeterministic and stochastic problems. We show initial findings and encourage\nfurther work in reinforcement learning driven by generative exploration.","url_abs":"http://arxiv.org/abs/1810.01112v1","url_pdf":"http://arxiv.org/pdf/1810.01112v1.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":"the-dreaming-variational-autoencoder-for","repo_url":"https://github.com/CAIR/deep-maze","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"management","task_name":"Management"},{"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=1810.01112","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}