Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning
This work addresses a specific bottleneck in MPC-based MBRL for robotics and simulation tasks, offering an incremental improvement over existing methods.
The paper tackles the bias in scoring trajectories using reward functions in MPC-based model-based reinforcement learning by proposing a novel scoring function based on the discounted sum of values, resulting in improved learning efficiency and average reward return in MuJoCo Gym environments and a simulated Cassie robot.
This paper proposes a novel scoring function for the planning module of MPC-based reinforcement learning methods to address the inherent bias of using the reward function to score trajectories. The proposed method enhances the learning efficiency of existing MPC-based MBRL methods using the discounted sum of values. The method utilizes optimal trajectories to guide policy learning and updates its state-action value function based on real-world and augmented onboard data. The learning efficiency of the proposed method is evaluated in selected MuJoCo Gym environments as well as in learning locomotion skills for a simulated model of the Cassie robot. The results demonstrate that the proposed method outperforms the current state-of-the-art algorithms in terms of learning efficiency and average reward return.