To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL

NeurIPSSpotlight2025

Authors
Yuda Song, Dhruv Rohatgi, Aarti Singh, Drew Bagnell
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Partial observability is a notorious challenge in reinforcement learning (RL), due to the need to learn complex, history-dependent policies…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

reinforcement learning

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive