Rajeev Alur

reinforcement learning (2) in-context learning (1) zero-sum game (1) multimodal learning (1) adversarial training (1) program synthesis (1) feature attribution (1) compositional learning (1) gradient estimation (1) hierarchical reinforcement learning (1) markov decision process (1) value iteration (1) reward function (1) lipschitz continuity (1) knowledge representation (1) deep neural network (1) foundation model (1) lipschitz constant (1) reward shaping (1) multi-agent reinforcement learning (1)