Internship: Safe and Robust Reinforcement Learning

  • Internship
Job expired!
The Dynamics team at MERL is looking for an enthusiastic and qualified individual to undertake research in safe robust reinforcement learning (RL). The perfect candidate should have a comprehensive background in RL, for example, Constrained Markov decision processes (CMDPs) and Robust MDPs theories. Familiarity with dynamical system theory and nonlinear control theory is an advantage, but not mandatory. It is expected that the results generated during the internship will be submitted, for instance, to ICML/ICLR/NeurIPS. The internship is projected to last 3 months with a flexible start date. Research Areas: Control, Dynamical Systems, Machine Learning Contact: Mouhacine Benosman Mitsubishi Electric Research Labs, Inc. "MERL" ensures equal employment opportunities (EEO) to all workers and applicants for employment without discrimination of race, color, religion, sex, nationality, age, disability, or genetics. In conformance with federal law necessities, MERL also abides by relevant state and local laws regulating nondiscrimination in employment in every location where the company has facilities. This policy encompasses all terms and conditions of employment including recruiting, hiring, placement, promotion, termination, layoff, recall, transfer, leaves of absence, remuneration, and training. MERL strictly forbids any form of workplace harassment based on race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status. Incorrect interference with the capacity of MERL’s employees to perform their job duties may result in discipline up to and including dismissal. Working at MERL necessitates full authorization to work in the U.S and access to technology, software, and other information subject to government access control restrictions, due to export controls. Continued full authorization to work in the U.S and the availability of government permission for the release of these items (which might require obtaining an export license or other documentation) are conditions of employment. To ensure practical compliance with applicable employment law and government access control restrictions, MERL may delay the start of employment, revoke an employment offer, terminate employment, and/or alter job responsibilities, compensation, benefits, and/or access to MERL facilities and information systems, as deemed appropriate by MERL.