alphaFeedback
CW

Caroline Wang

cs.AIcs.LGcs.MAcs.ROcs.HC

On Valency

published · living versions
W_hwfffymk·v1 · currentpublished
Centralized Critics for N-Agent Ad Hoc Teamwork
with Andrew McAlinden, Steven Shi, Arrasy Rahman, Elad Liebman +1
1 version

Preprints & journals

7 papers in the corpus · 2022–2026
JaxAHT: A JAX-Based Library for Ad Hoc Teamwork2609.13716v2 · Caroline Wang, Rolando Fernandez, Zelal Su Mustafaoglu et al.2026 · 0 citationsarXiv
Sequence Modeling for N-Agent Ad Hoc Teamwork2506.05527v3 · Caroline Wang, Di Yang Shi, Elad Liebman et al.2025 · 0 citationsarXiv
ROTATE: Regret-driven Open-ended Training for Ad Hoc Teamwork2505.23686v4 · Caroline Wang, Arrasy Rahman, Benjamin Nativi et al.2025 · 0 citationsarXiv
N-Agent Ad Hoc Teamwork2404.10740v3 · Caroline Wang, Arrasy Rahman, Ishan Durugkar et al.2024 · 0 citationsProceedings of the 38th International Conference on Neural Information Processing Systems (NIPS '24), Vol. 37 (2024), Article 3551, 111832-111862
Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning2401.12497v1 · Zizhao Wang, Caroline Wang, Xuesu Xiao et al.2024 · 3 citationsProceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI 2024), Article 1759, Pages 15778 - 15786
D-Shape: Demonstration-Shaped Reinforcement Learning via Goal Conditioning2210.14428v2 · Caroline Wang, Garrett Warnell, Peter Stone2022 · 1 citationAAMAS 2023: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems Pages 1267 - 1275
DM2^2: Decentralized Multi-Agent Reinforcement Learning for Distribution Matching2206.00233v3 · Caroline Wang, Ishan Durugkar, Elad Liebman et al.2022 · 1 citationProceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI 2023), Article 1313, Pages 11699 - 11707
Career total: 11 works. 7 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.