Computer Science Location: Zoom (contact presenter for link)
Add to Calendar 2022-06-10T10:00:00 2022-06-10T10:00:00 America/New_York PhD Qualifying Exam Presentation by Ingy ElSayed-Aly Logic-based Reward Shaping for Multi-Agent Reinforcement Learning   Abstract:   Zoom (contact presenter for link)

Logic-based Reward Shaping for Multi-Agent Reinforcement Learning

Reinforcement learning (RL) relies heavily on exploration to learn from its environment and maximize observed rewards. Therefore, it is essential to design a reward function that guarantees optimal learning from the received experience. Previous work has combined automata and logic based reward shaping with environment assumptions to provide an automatic mechanism to synthesize the reward function based on the task. However, there is limited work on how to expand logic-based reward shaping to Multi-Agent Reinforcement Learning (MARL).  The environment will need to consider the joint state in order to keep track of other agents if the task takes into account other agents, thus suffering from the curse of dimensionality. This project explores how logic-based reward shaping for MARL can be designed for different scenarios and tasks. We present a novel method ​for semi-centralized logic-based MARL reward shaping that is scalable in the number of agents and evaluate in multiple scenarios.


  • Hongning Wang, Committee Chair, (CS/SEAS/UVA)
  • Lu Feng, Advisor, (CS, ESE/SEAS/UVA)
  • Haifeng Xu (CS/SEAS/UVA)
  • Haiying Shen (CS/SEAS/UVA)