Multi-agent reinforcement learning: A selective overview of theories and algorithms
Recent years have witnessed significant advances in reinforcement learning (RL), which
has registered tremendous success in solving various sequential decision-making problems …
has registered tremendous success in solving various sequential decision-making problems …
Self-play reinforcement learning with comprehensive critic in computer games
Self-play reinforcement learning, where agents learn by playing with themselves, has been
successfully applied in many game scenarios. However, the training procedure for self-play …
successfully applied in many game scenarios. However, the training procedure for self-play …
Enhanced rolling horizon evolution algorithm with opponent model learning: Results for the fighting game AI competition
The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for two-
player video game artificial intelligence. The challenge arises from the large action space …
player video game artificial intelligence. The challenge arises from the large action space …
[PDF][PDF] Online Monte Carlo Counterfactual Regret Minimization for Search in Imperfect Information Games.
Online search in games has been a core interest of artificial intelligence. Search in imperfect
information games (eg, Poker, Bridge, Skat) is particularly challenging due to the …
information games (eg, Poker, Bridge, Skat) is particularly challenging due to the …
Ensemble strategy learning for imperfect information games
W Yuan, S Chen, P Li, J Chen - Neurocomputing, 2023 - Elsevier
Algorithms with several paradigms (such as rule-based methods, game theory and
reinforcement learning) have achieved great success in solving imperfect information games …
reinforcement learning) have achieved great success in solving imperfect information games …
[PDF][PDF] Smooth UCT Search in Computer Poker.
J Heinrich, D Silver - IJCAI, 2015 - davidsilver.uk
Abstract Self-play Monte Carlo Tree Search (MCTS) has been successful in many perfect-
information twoplayer games. Although these methods have been extended to imperfect …
information twoplayer games. Although these methods have been extended to imperfect …
[图书][B] The Governance cycle in parliamentary democracies
S De Marchi, M Laver - 2023 - books.google.com
Parliamentary democracy involves a never-ending cycle of elections, government
formations, and the need for governments to survive in potentially hostile environments …
formations, and the need for governments to survive in potentially hostile environments …
Don't Predict Counterfactual Values, Predict Expected Values Instead
J Wołosiuk, M Świechowski, J Mańdziuk - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Abstract Counterfactual Regret Minimization algorithms are the most popular way of
estimating the Nash Equilibrium in imperfect-information zero-sum games. In particular …
estimating the Nash Equilibrium in imperfect-information zero-sum games. In particular …
Monte Carlo tree search for games with hidden information and uncertainty
D Whitehouse - 2014 - etheses.whiterose.ac.uk
Monte Carlo Tree Search (MCTS) is an AI technique that has been successfully applied to
many deterministic games of perfect information, leading to large advances in a number of …
many deterministic games of perfect information, leading to large advances in a number of …
Emergent bluffing and inference with Monte Carlo tree search
PI Cowling, D Whitehouse… - 2015 IEEE conference on …, 2015 - ieeexplore.ieee.org
In many card and board games, players cannot see the whole game state, with different
players seeing different parts of the state. In such games, gathering of information …
players seeing different parts of the state. In such games, gathering of information …