RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning
This work addresses a specific issue in reinforcement learning for continuing tasks, offering an incremental improvement over existing methods.
The paper tackled the discrepancy between training objectives and performance metrics in continuing tasks by proposing RVI-SAC, an off-policy deep reinforcement learning method using the average reward criterion, which showed competitive performance on Gymnasium's Mujoco locomotion tasks.
In this paper, we propose an off-policy deep reinforcement learning (DRL) method utilizing the average reward criterion. While most existing DRL methods employ the discounted reward criterion, this can potentially lead to a discrepancy between the training objective and performance metrics in continuing tasks, making the average reward criterion a recommended alternative. We introduce RVI-SAC, an extension of the state-of-the-art off-policy DRL method, Soft Actor-Critic (SAC), to the average reward criterion. Our proposal consists of (1) Critic updates based on RVI Q-learning, (2) Actor updates introduced by the average reward soft policy improvement theorem, and (3) automatic adjustment of Reset Cost enabling the average reward reinforcement learning to be applied to tasks with termination. We apply our method to the Gymnasium's Mujoco tasks, a subset of locomotion tasks, and demonstrate that RVI-SAC shows competitive performance compared to existing methods.