Matthijs T. J. Spaan

reinforcement learning (3) safe policy improvement (3) sample complexity (2) sample efficiency (1) reinforcement learning theory (1) uncertainty quantification (1) structure learning (1) sequential decision making (1) bayesian regret (1) policy learning (1) distributional reinforcement learning (1) partially observable markov decision process (1) policy iteration (1) partially observable stochastic game (1) worst-case optimization (1) policy improvement (1) scalable training (1) monte carlo tree search (1) epistemic uncertainty (1) offline reinforcement learning (1)