Showing 2024Show all
3 papers · 1 filter
cs.RO2024
Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks
Jean Seong Bjorn Choe, Bumkyu Choi, Jong-kook Kim
This report presents a solution for the swing-up and stabilisation tasks of the acrobot and the pendubot, developed for the AI Olympics competition at IROS 2024. Our approach emplo…
cs.LG2024
Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation
Jean Seong Bjorn Choe, Jong-Kook Kim
Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objecti…
cs.LG2024
The Bid Picture: Auction-Inspired Multi-player Generative Adversarial Networks Training
Joo Yong Shim, Jean Seong Bjorn Choe, Jong-Kook Kim
This article proposes auction-inspired multi-player generative adversarial networks training, which mitigates the mode collapse problem of GANs. Mode collapse occurs when an over-f…