
Developing efficient algorithms for reinforcement learning with heavy-tailed rewards using linear function approximation.


coremsg

heavy-tailed-rewards-in-reinforcement-learning-with-function-approximation-algorithms-for-efficient-learning


Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Algorithms for Efficient Learning


title_rewrite


The author addresses the challenge of heavy-tailed rewards in reinforcement learning using linear function approximation, proposing novel algorithms HEAVY-OFUL and HEAVY-LSVI-UCB.


addressing-heavy-tailed-rewards-in-reinforcement-learning-with-linear-function-approximation


Addressing Heavy-Tailed Rewards in Reinforcement Learning with Linear Function Approximation
