Blar i ODA Open Digital Archive på forfatter "Meng, Li"

Viser treff 1-2 av 2

    • Improving the Diversity of Bootstrapped DQN by Replacing Priors With Noise 

      Meng, Li; Goodwin, Morten; Yazidi, Anis; Engelstad, Paal (Peer reviewed; Journal article, 2022)
      Q-learning is one of the most well-known Reinforcement Learning algorithms. There have been tremendous efforts to develop this algorithm using neural networks. Bootstrapped Deep Q-Learning Network is amongst them. It ...

    • Unsupervised State Representation Learning in Partially Observable Atari Games 

      Meng, Li; Goodwin, Morten; Yazidi, Anis; Engelstad, Paal E. (Lecture Notes in Computer Science;, Chapter; Peer reviewed; Conference object; Journal article, 2023)
      State representation learning aims to capture latent factors of an environment. Although some researchers realize the connections between masked image modeling and contrastive representation learning, the effort is focused ...