{"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/temporal-difference-variational-auto-encoder","title":"Temporal Difference Variational Auto-Encoder","arxiv_id":"1806.03107","date":"2018-06-08","proceeding":"ICLR 2019 5","authors":["Karol Gregor","George Papamakarios","Frederic Besse","Lars Buesing","Theophane Weber"],"abstract":"To act and plan in complex environments, we posit that agents should have a\nmental simulator of the world with three characteristics: (a) it should build\nan abstract state representing the condition of the world; (b) it should form a\nbelief which represents uncertainty on the world; (c) it should go beyond\nsimple step-by-step simulation, and exhibit temporal abstraction. Motivated by\nthe absence of a model satisfying all these requirements, we propose TD-VAE, a\ngenerative sequence model that learns representations containing explicit\nbeliefs about states several steps into the future, and that can be rolled out\ndirectly without single-step transitions. TD-VAE is trained on pairs of\ntemporally separated time points, using an analogue of temporal difference\nlearning used in reinforcement learning.","url_abs":"http://arxiv.org/abs/1806.03107v3","url_pdf":"http://arxiv.org/pdf/1806.03107v3.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":"temporal-difference-variational-auto-encoder","repo_url":"https://github.com/subinlab/model_based_rl_paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"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":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"td-vae","method_name":"TD-VAE"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"td-vae","name":"TD-VAE","full_name":"TD-VAE"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.03107","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}