Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts

This paper presents a method for acquiring diverse robot skills using curriculum reinforcement learning combined with a mixture of experts architecture, enabling agents to learn a versatile repertoire of behaviors.

Recommended citation: Onur Celik, Aleksandar Taranovic, Gerhard Neumann. (2024). "Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts." International Conference on Machine Learning (ICML).
Download Paper