activity
20222025
most citedBuilding Minimal and Reusable Causal State Abstractions for Reinforcement Learning

2 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.MAShow all

2 papers · 1 filter

cs.MA2025

Sequence Modeling for N-Agent Ad Hoc Teamwork

Caroline Wang, Di Yang Shi, Elad Liebman +3

N-agent ad hoc teamwork (NAHT) is a newly introduced challenge in multi-agent reinforcement learning, where controlled subteams of varying sizes must dynamically collaborate with v…

cs.MA2022★ 1 cited

DM: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching

Caroline Wang, Ishan Durugkar, Elad Liebman +1

Current approaches to multi-agent cooperation rely heavily on centralized mechanisms or explicit communication protocols to ensure convergence. This paper studies the problem of di…