Login / Signup

Efficient Reinforcement Learning via Decoupling Exploration and Utilization.

Jingpu YangHelin WangQirui ZhaoZhecheng ShiZirui SongMiao Fang
Published in: ICIC (2) (2024)
Keyphrases
  • reinforcement learning
  • lightweight
  • action selection
  • hidden markov models
  • input output
  • real world
  • learning algorithm
  • website
  • video sequences
  • control system
  • state space
  • computationally expensive
  • active exploration