Complex games have long been an important benchmark for testing the progress of artificial intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess, garnering widespread societal attention towards artificial intelligence. Concurrently, large language models (LLMs) have exhibited remarkable capabilities across various tasks, raising the question of whether LLMs can achieve similar success in complex games. In this paper, we explore the potential of LLMs in mastering complex card games. We systematically assess the learning capabilities of LLMs across eight diverse card games, evaluating the impact of fine-tuning on high-quality gameplay data, and examining the models' ability to retain general capabilities while mastering these games. Our findings indicate that: (1) LLMs can approach the performance of strong game AIs through supervised fine-tuning on high-quality data, (2) LLMs can achieve a certain level of proficiency in multiple complex card games simultaneously, with performance augmentation for games with similar rules and conflicts for dissimilar ones, and (3) LLMs experience a decline in general capabilities when mastering complex games, but this decline can be mitigated by integrating a certain amount of general instruction data. The evaluation results demonstrate strong learning ability and versatility of LLMs.

Complex games have long been an important benchmark for testing the progress of artificial intelligence algorithms. AlphaGo, AlphaZero, and MuZero have defeated top human players in Go and Chess, garnering widespread societal attention towards artificial intelligence. Concurrently, large language models (LLMs) have exhibited remarkable capabilities across various tasks, raising the question of whether LLMs can achieve similar success in complex games. In this paper, we explore the potential of LLMs in mastering complex card games. We systematically assess the learning capabilities of LLMs across eight diverse card games, evaluating the impact of fine-tuning on high-quality gameplay data, and examining the models' ability to retain general capabilities while mastering these games. Our findings indicate that: (1) LLMs can approach the performance of strong game AIs through supervised fine-tuning on high-quality data, (2) LLMs can achieve a certain level of proficiency in multiple complex card games simultaneously, with performance augmentation for games with similar rules and conflicts for dissimilar ones, and (3) LLMs experience a decline in general capabilities when mastering complex games, but this decline can be mitigated by integrating a certain amount of general instruction data. The evaluation results demonstrate strong learning ability and versatility of LLMs. The code is available at https://github.com/THUDM/LLM4CardGame

The smartest AI is a highly debated topic and can be defined in various ways depending on the context. However, some of the most advanced and widely recognized AI systems that are considered to be the "smartest" include: Watson is an AI system that was developed by IBM and is known for its ability to understand and respond to natural language. It uses machine learning algorithms and natural language processing to analyze and interpret large amounts of data, making it a powerful tool for businesses and researchers. Watson has been used in various applications such as medical diagnosis, financial analysis, and even in the game show Jeopardy! AlphaGo is an AI system developed by Google's DeepMind that is able to play the complex game of Go at a professional level.

Chess has long been regarded as one of the most intellectually challenging games in the world. It requires a deep understanding of strategy and the ability to anticipate and react to an opponent's moves. For years, chess has been dominated by human players who have honed their skills through years of practice and experience. However, in recent years, artificial intelligence has emerged as a formidable opponent on the chessboard. In 2017, Google's artificial intelligence company DeepMind introduced AlphaZero, an AI system that could teach itself how to play chess, shogi, and Go.

Two new papers from AI powerhouses DeepMind and Meta describe how AI systems are notching wins against human players in complex games involving deception, negotiation and cooperation. Why it matters: Machine contenders have struggled with games where information is incomplete or hidden from players -- similar to the intentions of humans in daily life and interactions. Driving the news: Researchers from DeepMind outline a new autonomous agent called "DeepNash" that learned to play the game Stratego in a paper published today in Science. How they did it: The DeepMind team combined an algorithm for learning the game through self-play and another that steers that learning toward an optimal strategy. Meta researchers last week described an AI system called "Cicero" that they report can play the game Diplomacy at the level of humans.

One of the major weaknesses of current real-time strategy (RTS) game agents is handling spatial reasoning at a high level. One challenge in developing spatial reasoning modules for RTS agents is to evaluate the ability of a given agent for this competency due to the inevitable confounding factors created by the complexity of these agents. We propose a simplified game that mimics spatial reasoning aspects of more complex games, while removing other complexities. Within this framework, we analyze the effectiveness of classical reinforcement learning for spatial management in order to build a detailed evaluative standard across a broad set of opponent strategies. We show that against a suite of opponents with fixed strategies, basic Q-learning is able to learn strategies to beat each. In addition, we demonstrate that performance against unseen strategies improves with prior training from other distinct strategies. We also test a modification of the basic algorithm to include multiple actors, to speed learning and increase scalability. Finally, we discuss the potential for knowledge transfer to more complex games with similar components.

CartPole, also known as inverted pendulum, is a game in which you try to balance the pole as long as possible. It is assumed that at the tip of the pole, there is an object which makes it unstable and very likely to fall over. The goal of this task is to move the cart left and right so that the pole can stand (within a certain angle) as long as possible. In this post, we will look at reinforcement learning, a field in artificial intelligence where the AI explores the environment all by itself by playing the game many many times until it learns the right way to play the game. As you can see here, at the beginning of the training, the agent has no idea of where to move a cart.

World-class human players have been outperformed in a number of complex two person games (Go, Chess, Checkers) by Deep Reinforcement Learning systems. However, owing to tractability considerations minimax regret of a learning system cannot be evaluated in such games. In this paper we consider simple games (Noughts-and-Crosses and Hexapawn) in which minimax regret can be efficiently evaluated. We use these games to compare Cumulative Minimax Regret for variants of both standard and deep reinforcement learning against two variants of a new Meta-Interpretive Learning system called MIGO. In our experiments all tested variants of both normal and deep reinforcement learning have worse performance (higher cumulative minimax regret) than both variants of MIGO on Noughts-and-Crosses and Hexapawn. Additionally, MIGO's learned rules are relatively easy to comprehend, and are demonstrated to achieve significant transfer learning in both directions between Noughts-and-Crosses and Hexapawn.

Between 9 and 15 March, 2016, the second-highest ranked Go player, Lee Sidol, took on a computer program named AlphaGo. AlphaGo emphatically outplayed and outclassed Mr. Sidol and won the series 4-1. Designed by Google's DeepMind, the program has spawned many other developments in AI, including AlphaGo Zero. These breakthroughs are widely considered as stepping stones towards Artificial General Intelligence (AGI). In this article, I will introduce you to the algorithm at the heart of AlphaGo – Monte Carlo Tree Search (MCTS). This algorithm has one main purpose – given the state of a game, choose the most promising move.

Artificial Intelligence and its associated technologies have become the buzzwords of companies, individuals and even governments. This begs the question; How did AI gain the prominence and attention it has today? What forced companies to stop and take notice of a technology that has effectively changed every walk of life? According to Google Trends, this phenomenon occurred around the beginning of 2016, with indexed search volume results almost doubling over just one month. However, the building blocks for the widespread adoption of AI had already been set. In 2011, IBM had debuted their Watson AI on the reality TV show Jeopardy!, where it was pitted against two of the best players in the world.