5 papers
Test-time Reinforcement Learning in Imperfect Information Games
Ondrej Kubicek, Viliam Lisy, Tuomas Sandholm
Test-time reasoning has significantly improved performance in domains ranging from games to language models. However, test-time policy changes with formal guarantees on the perform…
Equilibrium Refinements Improve Subgame Solving in Imperfect-Information Games
Ondrej Kubicek, Viliam Lisy, Tuomas Sandholm
Subgame solving is a technique for scaling algorithms to large games by locally refining a precomputed blueprint strategy during gameplay. While straightforward in perfect-informat…
Understanding Optimal Portfolios of Strategies for Solving Two-player Zero-sum Games
Karolina Drabent, Ondřej Kubíček, Viliam Lisý
In large-scale games, approximating the opponent's strategy space with a small portfolio of representative strategies is a common and powerful technique. However, the construction…
Look-ahead Reasoning with a Learned Model in Imperfect Information Games
Ondřej Kubíček, Viliam Lisý
Test-time reasoning significantly enhances pre-trained AI agents' performance. However, it requires an explicit environment model, often unavailable or overly complex in real-world…
Look-ahead Search on Top of Policy Networks in Imperfect Information Games
Ondrej Kubicek, Neil Burch, Viliam Lisy
Search in test time is often used to improve the performance of reinforcement learning algorithms. Performing theoretically sound search in fully adversarial two-player games with…