Novel function approximation techniques for large-scale reinforcement learning
Function approximation can be used to improve the performance of reinforcement learners. Traditional techniques, including Tile Coding and Kanerva Coding, can give poor performance when applied to large-scale problems. In our preliminary work, we show that this poor performance is caused by prototyp...
| Published: |
|
|---|---|
| Online Access: | http://hdl.handle.net/2047/d20000932 |