Recurrent World Models Facilitate Policy Evolution

On the reading lists

• #35 in Reinforcement learning (2026 edition)

Why it matters

Popularized learning compact generative environment models and training policies within imagined simulations.

Condensed from the expert lists' notes.

The record

First released

2018 (from arXiv 1803.10122)

Citations

2,233 citations, as counted by Papers With Code (CC BY-SA 4.0)

Named by

both expert lists

Score

0.269 · computed rank 681 · consensus 0.44, must-read 0, citations percentile 0.391 (2010s · reinforcement-learning), awards 0, existing lists 0. Method