<ul><li>Many dynamic decision problems, such as robotic control, involve diverse and unknown tasks at training time.</li><li>Existing approaches like multi-task and meta reinforcement learning struggle to generalize with task diversity.</li><li>This paper proposes a policy committee approach to address the challenges of task diversity.</li><li>Experiments demonstrate that the proposed approach outperforms existing baselines in training, generalization, and few-shot learning.</li></ul>

Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks

Discover more