20 citations · 35 across the 9 of their papers we have counts for
11 papers
Subgoal-Guided Policy Heuristic Search with Learned Subgoals
Jake Tuero, Michael Buro, Levi H. S. Lelis
Policy tree search is a family of tree search algorithms that use a policy to guide the search. These algorithms provide guarantees on the number of expansions required to solve a…
Transformer Based Planning in the Observation Space with Applications to Trick Taking Card Games
Douglas Rebstock, Christopher Solinas, Nathan R. Sturtevant +1
Traditional search algorithms have issues when applied to games of imperfect information where the number of possible underlying states and trajectories are very large. This challe…
History Filtering in Imperfect Information Games: Algorithms and Complexity
Christopher Solinas, Douglas Rebstock, Nathan R. Sturtevant +1
Historically applied exclusively to perfect information games, depth-limited search with value functions has been key to recent advances in AI for imperfect information games. Most…
Inference-Based Deterministic Messaging For Multi-Agent Communication
Varun Bhatt, Michael Buro
Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human commu…
Bayes DistNet -- A Robust Neural Network for Algorithm Runtime Distribution Predictions
Jake Tuero, Michael Buro
Randomized algorithms are used in many state-of-the-art solvers for constraint satisfaction problems (CSP) and Boolean satisfiability (SAT) problems. For many of these problems, th…
Single-Agent Optimization Through Policy Iteration Using Monte-Carlo Tree Search
Arta Seify, Michael Buro
The combination of Monte-Carlo Tree Search (MCTS) and deep reinforcement learning is state-of-the-art in two-player perfect-information games. In this paper, we describe a search a…