Yannis Flet-Berliac

Applications (1)

offline reinforcement learning (3) reinforcement learning (2) policy gradient (2) sample efficiency (1) sequential decision-making (1) model misspecification (1) supervised learning (1) batch reinforcement learning (1) policy selection (1) policy learning (1) model alignment (1) importance sampling (1) value function (1) continuous control (1) variance reduction (1) model-based reinforcement learning (1) preference optimization (1) off-policy learning (1) risk management (1) contrastive learning (1)