Jonathan Lee

Reinforcement Learning (1) Robotics (1)

reinforcement learning (4) model selection (3) contextual bandit (3) policy learning (3) function approximation (3) imitation learning (2) map inference (2) off-policy learning (2) message passing (2) entropy regularization (2) regret bound (2) linear programming relaxation (2) in-context learning (1) theorem proving (1) mathematical reasoning (1) offline reinforcement learning (1) image segmentation (1) scene understanding (1) bayesian inference (1) benchmark evaluation (1)