Yifan Yu

Informative Policy Representations in Multi-Agent Reinforcement Learning via Joint-Action Distributions.

2021 · arXiv (Cornell University)

In multi-agent reinforcement learning, the inherent non-stationarity of the environment caused by other agents' actions posed significant difficulties for an agent to learn a good policy independently. One way to deal with non-stationarity is agent …

Non-Exemplar Class-Incremental Learning via Adaptive Old Class Reconstruction

2023

In the Class-Incremental Learning (CIL) task, rehearsal-based approaches have received a lot of attention recently. However, storing old class samples is often infeasible in application scenarios where device memory is insufficient or data privacy is …