Login / Signup

A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning.

Siyuan GuoYanchao SunJifeng HuSili HuangHechang ChenHaiyin PiaoLichao SunYi Chang
Published in: CoRR (2023)
Keyphrases
  • reinforcement learning
  • main contribution
  • data sets
  • real time
  • databases
  • case study
  • markov decision processes
  • artificial intelligence
  • social networks
  • state space
  • theoretical framework
  • partial observability