Efficient Supervision for Robot Learning via Imitation, Simulation, and Adaptation by Wulfmeier, M

Mutual alignment transfer learning by Wulfmeier, M, Posner, H, Abbeel, P

Incremental adversarial domain adaptation for continually changing environments by Wulfmeier, M, Bewley, A, Posner, H

TACO: Learning task decomposition via temporal alignment for control by Shiarlis, K, Wulfmeier, M, Salter, S, Whiteson, S, Posner, H

Attention-privileged reinforcement learning by Salter, S, Rao, D, Wulfmeier, M, Hadsell, R, Posner, H

Large-scale cost function learning for path planning using deep inverse reinforcement learning by Wulfmeier, M, Rao, D, Wang, D, Ondruska, P, Posner, H

Neural stethoscopes: Unifying analytic, auxiliary and adversarial network probing by Fuchs, F, Groth, O, Kosiorek, A, Bewley, A, Wulfmeier, M, Vedaldi, A, Posner, H

Scrutinizing and de-biasing intuitive physics with neural stethoscopes by Fuchs, FB, Groth, O, Kosiorek, AR, Bewley, A, Wulfmeier, M, Vedaldi, A, Posner, I