Silviu Pitis

sequential decision making (2) counterfactual data augmentation (2) preference modeling (2) sample efficiency (2) preference learning (2) function approximation (1) markov decision process (1) decision theory (1) out-of-distribution generalization (1) language model alignment (1) offline reinforcement learning (1) discount factor (1) value function (1) model-based reinforcement learning (1) off-policy reinforcement learning (1) off-policy learning (1) sequential decision (1) temporal difference (1) multi-objective optimization (1) reward modeling (1)