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

26 October 2024

Jan Peters

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

1 / 1 papers shown

Title
Average-Reward Maximum Entropy Reinforcement Learning for Global Policy in Double Pendulum Tasks Jean Seong Bjorn Choe Bumkyu Choi Jong-kook Kim 31 0 0 12 May 2025