Solving the swing-up and balance task for the Acrobot and Pendubot with SAC

2023/12/18 by Chi Zhang, Zhang, Chi, Akhil Sathuluri +3
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO) #Traffic control and management

paper · pdf · doi:10.48550/arxiv.2312.11311

openalex publication_date 2023/12/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a solution of the swing-up and balance task for the pendubot and acrobot for the participation in the AI Olympics competition at IJCAI 2023. Our solution is based on the Soft Actor Crtic (SAC) reinforcement learning (RL) algorithm for training a policy for the swing-up and entering the region of attraction of a linear quadratic regulator(LQR) controller for stabilizing the double pendulum at the top position. Our controller achieves competitive scores in performance and robustness for both, pendubot and acrobot, problem scenarios.

Related

• Combining Deep Reinforcement Learning And Local Control For The Acrobot\n Swing-up And Balance Task
• Learning control of underactuated double pendulum with Model-Based Reinforcement Learning
• Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks
• Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks
• Real-Time Model Predictive Control for the Swing-Up Problem of an Underactuated Double Pendulum