RLvSL project page
Reinforcement Learning via Supervised Learning

Software

RCPI
The original Roll-out Classification Policy Iteration (RCPI) implementation (2003).
Download.
RSPI
The Roll-out Sampling Policy Iteration (RSPI) implementation (2008).
Download (coming soon).
ATPI
The Approximate Temporal Policy Iteration implementation.
Policy optimization for event-driven temporal processes.
Download (coming soon).