Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Wesley N. Kerr

Wesley N. Kerr

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2Game Theory×2ML×1Multiagent×1

Frequent co-authors

Chase McDonald2×
Nathan Tsang2×
Tristan Maidment1×
JB Lanier1×
Eugene Vinitsky1×
Roy Fox1×

Research Timeline

2026
EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

The paper introduces EMAgnet, a new regularization target for policy gradient methods that adapts to the agent's improving strategy.

FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

The paper introduces FootsiesGym, an open-source environment for learning in a two-player, zero-sum, imperfect-information game, providing a vectorized simulator for efficient analysis.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.GTEmpiricalRecentJul 7, 2026

FootsiesGym: A Fighting Game Benchmark for Two-Player Zero-Sum Imperfect-Information Games

Chase McDonald, Nathan Tsang, Wesley N. Kerr

The paper introduces FootsiesGym, an open-source environment for learning in a two-player, zero-sum, imperfect-information game, providing a vectorized simulator for efficient analysis.

View →
cs.LGcs.AIcs.GTEmpirical
Recent
Jun 22, 2026

EMAgnet: Parameter-Space EMA Regularization for Policy Gradient Self-Play in Large Games

Tristan Maidment, JB Lanier, Chase McDonald, Nathan Tsang +4 more

The paper introduces EMAgnet, a new regularization target for policy gradient methods that adapts to the agent's improving strategy.

View →