{"url":"/method/td-vae","slug":"td-vae","name":"TD-VAE","full_name":"TD-VAE","full_name_withheld":false,"description_markdown":"**TD-VAE**, or **Temporal Difference VAE**, is a generative sequence model that learns representations containing explicit beliefs about states several steps into the future, and that can be rolled out directly without single-step transitions. TD-VAE is trained on pairs of temporally separated time points, using an analogue of [temporal difference learning](https://paperswithcode.com/method/td-lambda) used in reinforcement learning.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Temporal Difference Variational Auto-Encoder","paper":"/paper/temporal-difference-variational-auto-encoder","first_author":"Karol Gregor","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/temporal-difference-variational-auto-encoder"},"source":{"url":"http://arxiv.org/abs/1806.03107v3","title":"Temporal Difference Variational Auto-Encoder","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"Sequential","area_id":"sequential","collection":"Generative Sequence Models","url":"/methods/category/generative-sequence-models","pwc_aliases":[]}],"n_papers_tagged":2,"archive_num_papers":2,"papers_newest_first":[{"paper":"/paper/a-temporal-variational-model-for-story","title":"A Temporal Variational Model for Story Generation","date":"2021-09-14","arxiv_id":"2109.06807","n_code_links":3,"syntology":null},{"paper":"/paper/temporal-difference-variational-auto-encoder","title":"Temporal Difference Variational Auto-Encoder","date":"2018-06-08","arxiv_id":"1806.03107","n_code_links":1,"syntology":null}],"papers_shown":2,"tasks":[{"task":"/task/diversity","name":"Diversity","papers":1},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":1},{"task":"/task/reinforcement-learning-1","name":"Reinforcement Learning (RL)","papers":1},{"task":"/task/reranking","name":"Reranking","papers":1},{"task":"/task/story-generation","name":"Story Generation","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1},{"task":"/task/model","name":"model","papers":1},{"task":"/task/reinforcement-learning-2","name":"reinforcement-learning","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2018","papers":1},{"year":"2021","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/td-vae"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}