Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Choe, Jean Seong Bjorn"'
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 employs the Average-Reward Entropy Advantage Policy Optimization (AR-EAPO),
Externí odkaz:
http://arxiv.org/abs/2409.08938
Autor:
Choe, Jean Seong Bjorn, Kim, Jong-Kook
Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising the expecte
Externí odkaz:
http://arxiv.org/abs/2407.18143
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-fitted generator generates a limited range of samples, often concentrat
Externí odkaz:
http://arxiv.org/abs/2403.13866