Reviewer2points out that "clarity for UED could be improved" with "a clearer description saying we haveX and28 wanttoachieveY".

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e.

We tackle the Multi-task Batch Reinforcement Learning problem. Given multiple datasets collected from different tasks, we train a multi-task policy to perform well in unseen tasks sampled from the same distribution. The task identities of the unseen tasks are not provided. To perform well, the policy must infer the task identity from collected transitions by modelling its dependency on states, actions and rewards. Because the different datasets may have state-action distributions with large divergence, the task inference module can learn to ignore the rewards and spuriously correlate \textit{only} state-action pairs to the task identity, leading to poor test time performance. To robustify task inference, we propose a novel application of the triplet loss.

The goal is to learn a single classifier that also performs well on all the tasks.