Thiago D. Simão

safe policy improvement (6) reinforcement learning (4) sample complexity (3) markov decision process (3) offline reinforcement learning (3) policy learning (2) sample efficiency (2) partially observable markov decision process (2) policy improvement (2) safe reinforcement learning (2) formal verification (1) sequential decision-making (1) sequential decision making (1) model uncertainty (1) structure learning (1) robust optimization (1) policy iteration (1) particle filtering (1) batch reinforcement learning (1) online planning (1)