Abstract
Reinforcement Learning (RL) for underactuated mechanical systems presents unique challenges due to the limited control inputs and complex dynamics of the system. Efficient exploration poses a significant problem for two reasons: First, these systems must start each episode of learning from an equilibrium position instead of a random position, severely limiting exploration. Second, these systems are often chaotic, which limits model-based exploration. To address these challenges, we introduce Energy-based Exploration for Reinforcement Learning (EBERL), which exploits a model of the system’s energy represented by a Deep Lagrangian Network (DeLaN), coupled to an energy-based controller to ensure goal-directed exploration on top of the exploration principles that are already present in RL. First, we validated our method in simulation on a Cartpole, Furuta pendulum and Pendubot with challenging torque constraints that cannot be solved by traditional methods. Additionally, we experimentally validated our method on the swing-up and stabilization of a Quanser QUBE2 Furuta pendulum.
Funding Information
  • Strategisch Basis Onderzoek (SBO) and CTRLxAI Project from Fonds Wetenschappelijk Onderzoek (FWO) Research Foundations Flanders (S007723N)

This publication has 29 references indexed in Scilit: