Fractional Moments on Bandit Problems
This addresses the challenge of efficient exploration in reinforcement learning for stateless environments, offering a novel algorithmic improvement with practical gains.
The paper tackles the explore-exploit dilemma in bandit problems by proposing a learning algorithm based on fractional expectation of rewards, which converges to an eta-optimal arm with O(n) sample complexity and achieves substantially lower regret than state-of-the-art methods in experiments.
Reinforcement learning addresses the dilemma between exploration to find profitable actions and exploitation to act according to the best observations already made. Bandit problems are one such class of problems in stateless environments that represent this explore/exploit situation. We propose a learning algorithm for bandit problems based on fractional expectation of rewards acquired. The algorithm is theoretically shown to converge on an eta-optimal arm and achieve O(n) sample complexity. Experimental results show the algorithm incurs substantially lower regrets than parameter-optimized eta-greedy and SoftMax approaches and other low sample complexity state-of-the-art techniques.