Skip to content

Latest commit

 

History

History
3 lines (3 loc) · 225 Bytes

File metadata and controls

3 lines (3 loc) · 225 Bytes

Deterministic-Control-in-Metric-Space

Implementation of upper-confidence reinforcement learning algorithm with nearest neighbor function approximator in the game cartpole. See https://arxiv.org/abs/1905.01576v1 for detail.