A Scalable Model-Free Recurrent Neural Network Framework for Solving POMDPs

@article{Liu2007ASM,
  title={A Scalable Model-Free Recurrent Neural Network Framework for Solving POMDPs},
  author={Zhenzhen Liu and Itamar Elhanany},
  journal={2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning},
  year={2007},
  pages={119-126}
}
This paper presents a framework for obtaining an optimal policy in model-free partially observable Markov decision problems (POMDPs) using a recurrent neural network (RNN), A Q-function approximation approach is taken, utilizing a novel RNN architecture with computation and storage requirements that are dramatically reduced when compared to existing schemes… CONTINUE READING