Clément Romac

large language model (2) contrastive learning (1) reinforcement learning (1) sample efficiency (1) policy learning (1) procedural generation (1) online reinforcement learning (1) contrastive loss (1) automatic curriculum learning (1) interactive environment (1) prompt overfitting (1) agent alignment (1) functional grounding (1) deep reinforcement learning (1) procedural task generation (1)