Velocity-History-Based Soft Actor-Critic Tackling IROS'24 Competition "AI Olympics with RealAIGym"

2024/10/26 by Tim Lukas Faust, Habib Maraqten, Faust, Tim Lukas +7 · 1 citation
Computer Science · Engineering · #Artificial Intelligence in Games #FOS: Computer and information sciences #Human Motion and Animation #Robotics (cs.RO) #Video Analysis and Summarization

paper · pdf · doi:10.48550/arxiv.2410.20096

openalex publication_date 2024/10/26 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28

Abstract

The ``AI Olympics with RealAIGym'' competition challenges participants to stabilize chaotic underactuated dynamical systems with advanced control algorithms. In this paper, we present a novel solution submitted to IROS'24 competition, which builds upon Soft Actor-Critic (SAC), a popular model-free entropy-regularized Reinforcement Learning (RL) algorithm. We add a `context' vector to the state, which encodes the immediate history via a Convolutional Neural Network (CNN) to counteract the unmodeled effects on the real system. Our method achieves high performance scores and competitive robustness scores on both tracks of the competition: Pendubot and Acrobot.

Cited by

• Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks

Related

• Soft Actor-Critic Algorithms and Applications
• Effective Reinforcement Learning Control using Conservative Soft Actor-Critic
• AI Olympics challenge with Evolutionary Soft Actor Critic
• Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor