Pretraining on noisy, internet-scale datasets has been heavily studied as a technique for
training models with broad, general capabilities for text, images, and other modalities …

Many reinforcement learning environments (eg Minecraft) provide only sparse rewards that
indicate task completion or failure with binary values. The challenge in exploration efficiency …

We study building a multi-task agent in Minecraft. Without human demonstrations, solving
long-horizon tasks in this open-ended environment with reinforcement learning (RL) is …

Open-ended algorithms aim to learn new, interesting behaviors forever. That requires a vast
environment search space, but there are thus infinitely many possible tasks. Even after …

We study building multi-task agents in open-world environments. Without human
demonstrations, learning to accomplish long-horizon tasks in a large open-world …

Deep reinforcement learning (RL) provides powerful methods for training optimal sequential
decision-making agents. As collecting real-world interactions can entail additional costs and …

One of the biggest challenges to modern deep reinforcement learning (DRL) algorithms is
sample efficiency. Many approaches learn a world model in order to train an agent entirely …