RLC 2026 Announces Outstanding Paper Awards; Chess Puzzle RL Work Among 7 Winners

allenainie · x · 2026-08-18

The Reinforcement Learning Conference (RLC 2026) announced seven Outstanding Paper Awards across categories. The Applications award went to "Discovering High Quality Chess Puzzles with Offline Reinforcement Learning" by Allen Nie (final PhD work advised by Emma Brunskill and Chris Piech) and colleagues. Other winners span offline hyperparameter selection, Q-learning for offline in-context RL, gradient iterated TD learning, RL for continual VLA learning, reward assignment from demonstrations, and the hardware-accelerated assistive robotics benchmark Assistax.

Original post →

More from Research

Research channel →