Logarithmic Regret for Reinforcement Learning with Linear Function Approximation

11/23/2020
by   Jiafan He, et al.
7

Reinforcement learning (RL) with linear function approximation has received increasing attention recently. However, existing work has focused on obtaining √(T)-type regret bound, where T is the number of steps. In this paper, we show that logarithmic regret is attainable under two recently proposed linear MDP assumptions provided that there exists a positive sub-optimality gap for the optimal action-value function. In specific, under the linear MDP assumption (Jin et al. 2019), the LSVI-UCB algorithm can achieve Õ(d^3H^5/gap_min·log(T)) regret; and under the linear mixture model assumption (Ayoub et al. 2020), the UCRL-VTR algorithm can achieve Õ(d^2H^5/gap_min·log^3(T)) regret, where d is the dimension of feature mapping, H is the length of episode, and gap_min is the minimum of sub-optimality gap. To the best of our knowledge, these are the first logarithmic regret bounds for RL with linear function approximation.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset