Anurag Ajay

Robotics (1)

distribution shift (2) foundation model (2) reinforcement learning (2) sample efficiency (1) bayesian inference (1) policy gradient (1) domain generalization (1) multimodal learning (1) empirical risk minimization (1) covariate shift (1) kalman filter (1) episodic memory (1) partially observable markov decision process (1) state estimation (1) inverse dynamics (1) continuous control (1) hierarchical planning (1) off-policy learning (1) off-policy reinforcement learning (1) offline reinforcement learning (1)