Mark Squillante

wasserstein distance (1) augmented lagrangian (1) stochastic optimization (1) multi-agent reinforcement learning (1) reinforcement learning (1) stochastic gradient descent (1) adversarial robustness (1) domain generalization (1) optimal transport (1) statistical convergence (1) distributed learning (1) decentralized optimization (1) robust reinforcement learning (1) formal verification (1) multi-agent learning (1) value function approximation (1) curse of dimensionality (1) bilevel optimization (1) bellman operator (1) model generalization (1)