Pierluca D'Oro

model-based reinforcement learning (2) policy optimization (2) policy gradient (2) visual grounding (1) regret minimization (1) importance sampling (1) policy search (1) multimodal large language model (1) randomized exploration (1) transition model (1) object hallucination (1) model learning (1) model-based rl (1) controlled decoding (1) batch policy improvement (1) reward-guided decoding (1) mediator feedback (1) reinforcement learning (1) action-value gradient (1) temporal difference learning (1)