Internship: Hierarchical Reinforcement Learning for Robotic Manipulation

MERL is seeking a highly driven individual to work on long-horizon planning and decision-making for robotic manipulation utilizing large language models (LLMs) and hierarchical RL. The research will feature the development of innovative algorithms for long-horizon task planning and execution using Hierarchical Reinforcement learning and LLMs. The ideal candidate should have experience in one or several of the following areas: (Deep) Reinforcement learning, Hierarchical RL, LLMs, policy optimization, and Markov Decision Processes (MDPs). Senior PhD students specializing in machine learning and engineering with a focus on Reinforcement Learning and robotics are invited to apply. Previous experience with physics engines like Mujoco, Isaac Gym, etc. is required. Experience with Python and ROS is also a requirement. A successful internship will lead to the submission of results to peer-reviewed conferences and journals. Good coding skills in Python and top-tier RL environments (e.g., RL Bench) are required. The internship is expected to last 3-4 months with flexible starting dates. This internship is preferably onsite at MERL. Research Areas: Artificial Intelligence, Machine Learning, Robotics Contact: Devesh Jha Mitsubishi Electric Research Labs, Inc. "MERL" is an equal opportunity employer. All employees and applicants for employment are treated without regard to race, color, religion, sex, national origin, age, disability, or genetics. In addition to being compliant with federal law requirements, MERL also adheres to applicable state and local laws governing nondiscrimination in employment. This policy covers all terms and conditions of employment, including recruitment, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, compensation, and training. Moreover, any form of workplace harassment is prohibited at MERL based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. Any inappropriate interference with the ability of MERL’s employees to perform their job duties may result in discipline up to and including discharge. Working at MERL requires complete authorization to work in the U.S and access to technology, software, and other information subject to governmental access control restrictions, due to export controls. Employment is conditioned on continued full authorization to work in the U.S and the ability to obtain government authorization for the release of these items, which could necessitate obtaining an export license or other documentation. MERL may delay commencement of employment, rescind a job offer, terminate employment, and/or modify job responsibilities, compensation, benefits, and/or access to MERL facilities and information systems, according to their discretion, to ensure practical compliance with employment law and government access control restrictions.