Methods › Sequential › Generative Sequence Models › TD-VAE
TD-VAE
Introduced by Karol Gregor et al. in Temporal Difference Variational Auto-Encoder
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 used in reinforcement learning.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
A Temporal Variational Model for Story Generation 14 Sep 2021 · 3 repositories · arXiv:2109.06807
-
Temporal Difference Variational Auto-Encoder 8 Jun 2018 · 1 repository · arXiv:1806.03107
Tasks archive 2025-07-28
8 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Diversity | 1 |
| Reinforcement Learning | 1 |
| Reinforcement Learning (RL) | 1 |
| Reranking | 1 |
| Story Generation | 1 |
| Text Generation | 1 |
| model | 1 |
| reinforcement-learning | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections