Empowered by neural networks, deep reinforcement learning (DRL) achieves tremendous empirical success. However, DRL requires a large dataset by interacting with the environment, which is unrealistic in critical scenarios such as autonomous driving and personalized medicine. In this paper, we study how to incorporate the dataset collected in the offline setting to improve the sample efficiency in the online setting. To incorporate the observational data, we face two challenges.

Our empirical results demonstrate that our method outperforms representative GNN baselines in terms of solution accuracy and inference speed as well asconventional solverslikeGurobi with limited time budgets.

Different from the original MoCo [19] and its cross-modal versions [15, 33, 35] that utilize momentum update for only momentum encoders to maintain a large consistent queue, our BMU strategy imposes momentum update on both momentum encoders and (video/text) encoders.

We reveal which problems in unbalanced optimal transport can/cannot be solved efficiently.

We demonstrate this by deriving an upper bound on theRademacher Complexitythatdepends ontwokeyquantities: (i)theintrinsic dimension, which is a measure of isotropy, and (ii) the largest eigenvalue of the second moment (covariance) matrix ofthe distribution.