Projects

• SafeCampus-Multidiscrete — A single-agent reinforcement learning environment and q learning algorithms for optimizing classroom occupancy during epidemics. View on GitHub
• SafeCampus-Multiclassroom — This project implements a reinforcement learning approach to optimize classroom policies in a multi-classroom environment during a pandemic scenario.. View on GitHub
• Sentimental Agents — Collaboration project that implements a LLM-based Multiagent Simulation framework for evaluating Opinion Dynamics in LLM-based agents for augmenting organizational decision making.. View on GitHub
• Fair-MARL — Collaboration project implements a Fair Multi-Agent Reinforcement Learning (Fair-MARL) framework that performs preference-aware and fairness-constrained goal assignments in decentralized environments. View on GitHub