Dream to Control: Learning Behaviors by Latent Imagination

On the reading lists

• #31 in Reinforcement learning (2026 edition)

Why it matters

Established efficient policy learning by differentiating through imagined trajectories in latent dynamics models.

Condensed from the expert lists' notes.

The record

First released

2019 (from arXiv 1912.01603)

Citations

2,438 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Score

0.310 · computed rank 580 · consensus 0.45, must-read 0, citations percentile 0.5 (2010s · reinforcement-learning), awards 0, existing lists 0. Method