2 papers
cs.LG2025
Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions
Can Cömer, Jannis Blüml, Cedric Derstroff +1
Monte Carlo Tree Search (MCTS) has proven effective in solving decision-making problems in perfect information settings. However, its application to stochastic and imperfect inform…
cs.LG2023
From Images to Connections: Can DQN with GNNs learn the Strategic Game of Hex?
Yannik Keller, Jannis Blüml, Gopika Sudhakaran +1
The gameplay of strategic board games such as chess, Go and Hex is often characterized by combinatorial, relational structures -- capturing distinct interactions and non-local patt…