Reinforcement-Learning Researcher

About the role

Reinforcement-Learning (RL) Researchers focus on reward-based learning systems and human feedback.

Responsibilities

• Develop RL algorithms: Create new methods for reinforcement and inverse reinforcement learning.
• Implement human-in-the-loop systems: Integrate human feedback into training processes.
• Design environments and simulations: Build realistic environments to train RL agents safely.
• Analyze stability and convergence: Study theoretical properties of RL methods to ensure reliable performance.

Qualifications

• PhD in machine learning, control theory, or related field.
• Strong background in RL theory, human-robot interaction, and simulation tools.