2 papers
cs.LG2025
Multi-agent Markov Entanglement
Shuze Chen, Tianyi Peng
Value decomposition has long been a fundamental technique in multi-agent dynamic programming and reinforcement learning (RL). Specifically, the value function of a global state $(s…
cs.SI2025
Differences-in-Neighbors for Network Interference in Experiments
Tianyi Peng, Naimeng Ye, Andrew Zheng
Experiments in online platforms frequently suffer from network interference, in which a treatment applied to a given unit affects outcomes for other units connected via the platfor…