Timothy Mann

temporal abstraction (2) option framework (2) neural network verification (2) adversarial robustness (2) bayesian learning (1) model misspecification (1) policy evaluation (1) adversarial training (1) domain generalization (1) robust reinforcement learning (1) formal verification (1) model-based reinforcement learning (1) skill discovery (1) off-policy learning (1) policy learning (1) approximate value iteration (1) lagrangian relaxation (1) bellman operator (1) generative model (1) model-based learning (1)