This National Science Foundation (NSF) Project Grant award under the Computer and Information Science and Engineering (CFDA 47.070) program provides $290,739 to Portland State University (PSU) to research and develop new technologies to close the simulation-to-reality gap in reinforcement learning (RL).
The project aims to advance RL techniques through three key mechanisms: randomization to generate a diverse set of simulators, alignment to make simulators more representative of the real world, and derivation to directly learn optimal policies from offline real-world data. These innovations are expected to improve the availability, applicability, and generalization of RL, minimizing the gap between common RL practices and real-world deployment. The award period runs from September 1, 2024 to August 31, 2027.
Generated 1/28/25, 10:38 AM