Research Statement

I am broadly interested in practical deep reinforcement learning algorithms to solve complex tasks, especially applied to robotics. As such, my work draws in elements from machine learning, computer vision, and robotics. Some particular areas of focus include imitation learning and leveraging prior knowledge, and improving collaboration between humans and robots.


  1. (Journal) Using machine learning to reduce observational biases when detecting new impacts on Mars Wagstaff, K.L., Daubar, I.J., Doran, G., Munje, M.J., Bickel, V.T., Gao, A., Pate, J. and Wexler, D., 2022. Icarus, 386, p.115146.

  2. (Journal) Reconfiguration of connected graph partitions Akitaya, H.A., Jones, M.D., Korman, M., Korten, O., Meierfrankenfeld, C., Munje, M.J., Souvaine, D.L., Thramann, M. and Toth, C.D., 2019. Journal of Graph Theory.

  3. (Conference) Towards a systems programming language designed for hierarchical state machines. McClelland, B., Tellier, D., Millman, M., Go, K.B., Balayan, A., Munje, M.J., Dewey, K., Ho, N., Havelund, K. and Ingham, M., 2021, July. In 2021 IEEE 8th International Conference on Space Mission Challenges for Information Technology (SMC-IT) (pp. 23-30). IEEE.

  4. (Consortium, 2-page Abstract) Large-scale automated detection of fresh impacts on Mars using machine learning with CTX observations. Munje, M.J., Daubar, I.J., Doran, G., Wagstaff, K.L. and Mandrake, L., 2020, August. In 11th Planetary Crater Consortium Meeting (Vol. 11, No. 2251, p. 2065).