Login / Signup

Reinforcement Learning from Bagged Reward: A Transformer-based Approach for Instance-Level Reward Redistribution.

Yuting TangXin-Qiang CaiYao-Xiang DingQiyu WuGuoqing LiuMasashi Sugiyama
Published in: CoRR (2024)
Keyphrases
  • reinforcement learning
  • instance level
  • state space
  • learning algorithm
  • reward function
  • supervised learning
  • optimal policy
  • multiple instance
  • pairwise
  • learning process
  • transfer learning
  • random forests