Projects

A Skill-Driven Skill-Recombination Algorithm for Efficient Policy Learning

Introduce a novel algorithm, SDSRA, an innovative framework that significantly enhances the efficiency of achieving maximum entropy in reinforcement learning tasks. We find that SDSRA achieves faster convergence compared to the traditional Soft Actor-Critic (SAC) algorithm and produces improved policies. By integrating skill-based strategies within the robust Actor-Critic framework, SDSRA demonstrates remarkable adaptability and performance across a wide array of complex and diverse benchmarks.

All Aboard App

All Aboard is a cutting-edge app designed to assist individuals with visual impairments by utilizing object detection technology to identify bus stops. This app provides intuitive visual cues and is available for download on both Google Play Store and Apple App Store.  (https://blogs.microsoft.com/accessibility/all-aboard-an-ai-based-mobile-app-is-making-bus-stops-more-accessible/ )

Download:

https://apps.apple.com/us/app/all-aboard/id1580638469