Model-based Reinforcement Learning for Parameterized Action Spaces

arXiv:2404.03037v1 Announce Type: new
Abstract: 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). The agent learns a parameterized-action-conditioned dynamics model and plans with a modified Model Predictive Path Integral control. We theoretically quantify the difference between the generated trajectory and the optimal trajectory during planning in terms of the value they achieved through the lens of Lipschitz Continuity. Our empirical results on …

abstract agent algorithm arxiv control cs.ai cs.lg decision difference dynamics integral markov novel path predictive processes reinforcement reinforcement learning spaces type