Internship: Inverse Reinforcement Learning

Cambridge, Massachusetts, United States · DA · 1188


MERL is looking for a highly motivated intern to develop reinforcement learning algorithms for problems with high-dimensional state and action spaces. The focus is on inverse reinforcement learning, i.e., estimating the reward function from observing demonstration data. Successful candidate will collaborate with MERL researchers to design, analyze, and implement new algorithms, conduct experiments, and prepare results for publication. The candidate should have a strong background in reinforcement learning and machine learning/statistics. The candidate should be comfortable implementing algorithms in Python. Prior exposure to deep learning and hands-on experience with packages such as Keras, TensorFlow, or Theano is a plus. The candidate is expected to be a PhD student in Computer Science, Electrical Engineering, Operations Research, Statistics, Applied Mathematics, or a related field, with relevant publication record. The duration of the internship is 12 weeks. The starting date is flexible and can be as early as April 2018.

Research Area: Data Analytics

Contact: Amir-massoud Farahmand

Apply for this job