Article

SMM-AC: Regularized reinforcement learning improves sim-to-real transfer

The authors propose SMM-AC, a regularized reinforcement learning algorithm based on the soft mellowmax value function. On MuJoCo continuous control benchmarks it is comparable to baselines such as SAC, and on real robots it achieves higher returns while being more robust to perturbations in observations, the environment, and dynamics. The study compares the sim-to-real transfer performance of commonly used reinforcement learning algorithms and finds that regularization improves policy robustness to the sim-to-real gap and to real-world environment changes.

Part of the event: SMM-AC: Regularized Reinforcement Learning Improves Real-Robot Transfer

This page provides a summary and source link only.