Assistive agents should make humans' lives easier.

All the code and data are open-sourced at our website.

Domain transfer methods aim to bridge this dynamics gap through techniques such as domain adaptation or domain calibration.

In a standard view of the reinforcement learning problem, an agent's goal is to efficiently identify a policy that maximizes long-term reward.

Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model.