Heinz Koeppl

variational inference (10) mean field game (4) bayesian inference (3) continuous-time bayesian network (3) stochastic differential equation (3) switching dynamical system (2) deep reinforcement learning (2) continuous time (2) parameter inference (2) markov decision process (2) gibbs sampler (2) fictitious play (2) structure learning (2) markov jump process (2) inverse reinforcement learning (2) equilibrium learning (2) imitation learning (2) stochastic control (2) bounded rationality (1) approximate inference (1)