Superhuman AI for two-player Catan

In earlier work, we trained two-player Catan agents with a three-step recipe. A network is trained by behavior cloning on the combined moves of several teacher networks, then by reinforcement learning from self-play, and the network plays with a paired-rollout search. Here we apply the recipe again to train a second generation, with one teacher descended from the first. In a series of 100 ranked games on an online two-player ladder, the resulting agent won 74 of 89 games, 83.1% (74.0 to 89.5), against opponents in the top 4% of the more than 55,000 players ranked in the ladder's previous season. Against opponents of the same ratings, the top 0.1% of those players won 62.7% (56.0 to 69.5). The difference is 20.4 percentage points (10.1 to 30.7), on a test and reference fixed before the account's first game. With each opponent rated at their displayed rating going into the game, the difference is 25.0 percentage points (15.2 to 34.8). During the series, the account's displayed rating reached the highest rating recorded for any player in the ladder's history, and the account ranked first on the ladder. Self-play training did not make the network statistically significantly stronger without search. With search, self-play training raised the win rate by 1.7 percentage points (0.7 to 2.8), statistically significant at the 5% level.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-18
DOI
https://doi.org/10.5281/zenodo.24353439
Primary Topic
Artificial Intelligence in Games
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Superhuman AI for two-player Catan

Brian St. Marie
1 links
Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Games
preprint

Superhuman AI for two-player Catan

Brian St. Marie
preprint en

Abstract

In earlier work, we trained two-player Catan agents with a three-step recipe. A network is trained by behavior cloning on the combined moves of several teacher networks, then by reinforcement learning from self-play, and the network plays with a paired-rollout search. Here we apply the recipe again to train a second generation, with one teacher descended from the first. In a series of 100 ranked games on an online two-player ladder, the resulting agent won 74 of 89 games, 83.1% (74.0 to 89.5), against opponents in the top 4% of the more than 55,000 players ranked in the ladder's previous season. Against opponents of the same ratings, the top 0.1% of those players won 62.7% (56.0 to 69.5). The difference is 20.4 percentage points (10.1 to 30.7), on a test and reference fixed before the account's first game. With each opponent rated at their displayed rating going into the game, the difference is 25.0 percentage points (15.2 to 34.8). During the series, the account's displayed rating reached the highest rating recorded for any player in the ladder's history, and the account ranked first on the ladder. Self-play training did not make the network statistically significantly stronger without search. With search, self-play training raised the win rate by 1.7 percentage points (0.7 to 2.8), statistically significant at the 5% level.

Zenodo (CERN European Organization for Nuclear Research)
Artificial Intelligence in Games
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon