$β$-DQN: Improving Deep Q-Learning By Evolving the Behavior
This provides an incremental improvement for researchers and practitioners in reinforcement learning by offering a simple and efficient exploration method.
The paper tackles the problem of inefficient exploration in deep reinforcement learning by introducing $\beta$-DQN, a method that uses a behavior function to generate diverse policies and an adaptive meta-controller for selection, resulting in outperformance over baseline methods across various tasks.
While many sophisticated exploration methods have been proposed, their lack of generality and high computational cost often lead researchers to favor simpler methods like $ε$-greedy. Motivated by this, we introduce $β$-DQN, a simple and efficient exploration method that augments the standard DQN with a behavior function $β$. This function estimates the probability that each action has been taken at each state. By leveraging $β$, we generate a population of diverse policies that balance exploration between state-action coverage and overestimation bias correction. An adaptive meta-controller is designed to select an effective policy for each episode, enabling flexible and explainable exploration. $β$-DQN is straightforward to implement and adds minimal computational overhead to the standard DQN. Experiments on both simple and challenging exploration domains show that $β$-DQN outperforms existing baseline methods across a wide range of tasks, providing an effective solution for improving exploration in deep reinforcement learning.