Discovering Options for Exploration by Minimizing Cover Time
This addresses the problem of slow exploration in sparse-reward tasks for reinforcement learning practitioners, offering a method to accelerate learning.
The paper tackles the challenge of sparse rewards in reinforcement learning by showing that the difficulty of discovering distant rewarding states is bounded by the expected cover time of a random walk, and proposes an algorithm that constructs options to minimize cover time, empirically improving learning time in several domains.
One of the main challenges in reinforcement learning is solving tasks with sparse reward. We show that the difficulty of discovering a distant rewarding state in an MDP is bounded by the expected cover time of a random walk over the graph induced by the MDP's transition dynamics. We therefore propose to accelerate exploration by constructing options that minimize cover time. The proposed algorithm finds an option which provably diminishes the expected number of steps to visit every state in the state space by a uniform random walk. We show empirically that the proposed algorithm improves the learning time in several domains with sparse rewards.