Gao Peng

Gao Peng is a PhD student at CWI, specializing in reinforcement learning and game theory. His PhD project focuses on multi-objective (multi-agent) reinforcement learning, aiming to enable intelligent decision-making in complex environments involving multiple objectives, partial observation, and numerous agents. In the A4E project, Gao conducts fundamental research inspired by energy transition scenarios, where users face conflicting objectives and multiple decision-makers. His long-term goal is to advance the capability of agents to approach optimal decisions in such challenging settings.

Research topic/responsibility within Align4energy
Multi-Objective and Multi-Agent Reinforcement Learning with a Use Case in Energy Transition