Ran Tian

Simple Recurrence Improves Masked Language Models

2022 · arXiv (Cornell University)

In this work, we explore whether modeling recurrence into the Transformer architecture can both be beneficial and efficient, by building an extremely simple recurrent module into the Transformer. We compare our model to baselines following …

Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization

2023 · arXiv (Cornell University)

Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination of this …