Model-based Reinforcement Learning for Parameterized Action Spaces

1 code implementation • 3 Apr 2024 • Renhao Zhang, Haotian Fu, Yilin Miao, George Konidaris

We propose a novel model-based reinforcement learning algorithm -- Dynamics Learning and predictive control with Parameterized Actions (DLPA) -- for Parameterized Action Markov Decision Processes (PAMDPs).

Model-based Reinforcement Learning reinforcement-learning