Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation

@article{Fujita2007ModelBasedRL,
  title={Model-Based Reinforcement Learning for Partially Observable Games with Sampling-Based State Estimation},
  author={Hajime Fujita and Shin Ishii},
  journal={Neural Computation},
  year={2007},
  volume={19},
  pages={3051-3087}
}
Games constitute a challenging domain of reinforcement learning (RL) for acquiring strategies because many of them include multiple players and many unobservable variables in a large state space. The difficulty of solving such realistic multiagent problems with partial observability arises mainly from the fact that the computational cost for the estimation… CONTINUE READING