Reinforcement Learning in Continuous Time and Space: Interference and Not Ill Conditioning Is the Main Problem When Using Distributed Function Approximators

@article{Baddeley2008ReinforcementLI,
  title={Reinforcement Learning in Continuous Time and Space: Interference and Not Ill Conditioning Is the Main Problem When Using Distributed Function Approximators},
  author={B. Baddeley},
  journal={IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)},
  year={2008},
  volume={38},
  pages={950-956}
}
Many interesting problems in reinforcement learning (RL) are continuous and/or high dimensional, and in this instance, RL techniques require the use of function approximators for learning value functions and policies. Often, local linear models have been preferred over distributed nonlinear models for function approximation in RL. We suggest that one reason… CONTINUE READING