Login / Signup

ESRL: Efficient Sampling-Based Reinforcement Learning for Sequence Generation.

Chenglong WangHang ZhouYimin HuYifu HuoBei LiTongran LiuTong XiaoJingbo Zhu
Published in: AAAI (2024)
Keyphrases
  • reinforcement learning
  • neural network
  • monte carlo
  • real time
  • databases
  • learning process
  • computationally efficient
  • cost effective
  • computationally expensive