The reviewed record of science sign in
Pith

arxiv: 2209.08169 · v2 · pith:TMEZLTRL · submitted 2022-09-16 · cs.LG · cs.RO

Value Summation: A Novel Scoring Function for MPC-based Model-based Reinforcement Learning

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:TMEZLTRLrecord.jsonopen to challenge →

classification cs.LG cs.RO
keywords learningfunctionmethodefficiencympc-basedproposedmethodsnovel
0
0 comments X
read the original abstract

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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.