<ul><li>Reward functions are central in reinforcement learning (RL), guiding agents towards optimal decision-making.</li><li>Effective reward design aims to provide signals that accelerate the agent's convergence to optimal behavior.</li><li>This thesis investigates different aspects of reward shaping, including teacher-driven, adaptive interpretable reward design, and agent-driven approaches.</li><li>The research explores the impact of reward signals on the agent's behavior and learning dynamics and addresses challenges such as delayed, ambiguous, or intricate rewards.</li></ul>

Reward Design for Reinforcement Learning Agents

Discover more