Provably Efficient Q-learning for Robust Reinforcement Learning
arXiv:2610.35656v1 Announce Type: new Abstract: Standard reinforcement learning (RL) algorithms based on Markov Decision Processes (MDPs) are vulnerable to sim-to-real gaps. To address this issue, distributionally robust RL algorithms based on robust MDPs (RMDPs) have been proposed, for ensuring th…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-27 04:00 · arXiv stat.ML
Provably Efficient Q-learning for Robust Reinforcement Learning