Skip to main content

1 Result(s)

within Computer Science Remove this filter Algorithm Analysis and Problem Complexity Remove this filter Computation by Abstract Devices Remove this filter Computer Communication Networks Remove this filter Hirotaka Kameko Remove this filter

and

  1. No Access

    Chapter and Conference Paper

    Exploration Bonuses Based on Upper Confidence Bounds for Sparse Reward Games

    Recent deep reinforcement learning (RL) algorithms have achieved super-human-level performance in many Atari games. However, a closer look at their performance reveals that the algorithms fall short of humans ...

    Naoki Mizukami, Jun Suzuki, Hirotaka Kameko… in Advances in Computer Games (2017)