Jump-Start Reinforcement Learning
Ikechukwu Uchendu,u00a0Ted Xiao,u00a0Yao Lu,u00a0Banghua Zhu,u00a0Mengyuan Yan,u00a0Josu00e9phine Simon,u00a0Matthew Bennice,u00a0Chuyuan Fu,u00a0Cong Ma,u00a0Jiantao Jiao,u00a0Sergey Levine,u00a0Karol Hausman
Reinforcement learning (RL) provides a theoretical framework for continuously improving an agentu2019s behavior via trial and error. However, efficiently learning policies from scratch can be very difficult, particularly for tasks that present exploration challenges. In such settings, it might be desirable to initialize RL with an existing policy, offline data, or demonstrations. However, naively performing such initialization in RL often works poorly, especially for value-based methods. In this paper, we present a meta algorithm that can use offline data, demonstrations, or a pre-existing policy to initialize an RL policy, and is compatible with any RL approach. In particular, we propose Jump-Start Reinforcement Learning (JSRL), an algorithm that employs two policies to solve tasks: a guide-policy, and an exploration-policy. By using the guide-policy to form a curriculum of starting states for the exploration-policy, we are able to efficiently improve performance on a set of simulated robotic tasks. We show via experiments that it is able to significantly outperform existing imitation and reinforcement learning algorithms, particularly in the small-data regime. In addition, we provide an upper bound on the sample complexity of JSRL and show that with the help of a guide-policy, one can improve the sample complexity for non-optimism exploration methods from exponential in horizon to polynomial.
