Jonathan How

gaussian process (2) online learning (1) landmark selection (1) policy optimization (1) real-time control (1) policy gradient (1) risk-aware planning (1) model fusion (1) model-free reinforcement learning (1) importance sampling (1) policy search (1) partially observable markov decision process (1) model-based reinforcement learning (1) budgeted optimization (1) probabilistic modeling (1) submodular maximization (1) approximation algorithm (1) information gain (1) sample efficiency (1) multi-agent reinforcement learning (1)