Rényi State Entropy for Exploration Acceleration in Reinforcement Learning
This work addresses the challenge of sustainable exploration for reinforcement learning agents, representing an incremental improvement over prior intrinsic reward methods.
The paper tackled the problem of vanishing intrinsic rewards in deep reinforcement learning by proposing a novel intrinsic reward module based on Rényi entropy, which achieved higher performance compared to existing schemes in simulations.
One of the most critical challenges in deep reinforcement learning is to maintain the long-term exploration capability of the agent. To tackle this problem, it has been recently proposed to provide intrinsic rewards for the agent to encourage exploration. However, most existing intrinsic reward-based methods proposed in the literature fail to provide sustainable exploration incentives, a problem known as vanishing rewards. In addition, these conventional methods incur complex models and additional memory in their learning procedures, resulting in high computational complexity and low robustness. In this work, a novel intrinsic reward module based on the Rényi entropy is proposed to provide high-quality intrinsic rewards. It is shown that the proposed method actually generalizes the existing state entropy maximization methods. In particular, a $k$-nearest neighbor estimator is introduced for entropy estimation while a $k$-value search method is designed to guarantee the estimation accuracy. Extensive simulation results demonstrate that the proposed Rényi entropy-based method can achieve higher performance as compared to existing schemes.