Related papers: Tackling Morpion Solitaire with AlphaZero-likeRank…

We present Self-Play Preference Optimization (SPO), an algorithm for reinforcement learning from human feedback. Our approach is minimalist in that it does not require training a reward model nor unstable adversarial training and is…

The 20 Questions (Q20) game is a well known game which encourages deductive reasoning and creativity. In the game, the answerer first thinks of an object such as a famous person or a kind of animal. Then the questioner tries to guess the…

Large Language Models (LLM) are increasingly being explored for problem-solving tasks. However, their strategic planning capability is often viewed with skepticism. Recent studies have incorporated the Monte Carlo Tree Search (MCTS)…

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered great success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g.,…

Deep reinforcement learning methods traditionally struggle with tasks where environment rewards are particularly sparse. One successful method of guiding exploration in these domains is to imitate trajectories provided by a human…

Counterfactual regret minimization (CFR) is a popular method to deal with decision-making problems of two-player zero-sum games with imperfect information. Unlike existing studies that mostly explore for solving larger scale problems or…

How to best explore in domains with sparse, delayed, and deceptive rewards is an important open problem for reinforcement learning (RL). This paper considers one such domain, the recently-proposed multi-agent benchmark of Pommerman. This…

Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for…

In many problem settings, most notably in game playing, an agent receives a possibly delayed reward for its actions. Often, those rewards are handcrafted and not naturally given. Even simple terminal-only rewards, like winning equals 1 and…

Learning agents that excel at sequential decision-making tasks must continuously resolve the problem of exploration and exploitation for optimal learning. However, such interactions with the environment online might be prohibitively…

While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the…

This paper investigates a class of multi-player discrete games where each player aims to maximize its own utility function. Each player does not know the other players' action sets, their deployed actions or the structures of its own or the…

Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience…

We propose a decentralized solution for a pursuit-evasion game involving a heterogeneous group of rational (selfish) pursuers and a single evader based on the framework of potential games. In the proposed game, the evader aims to delay (or,…

In repeated stochastic games (RSGs), an agent must quickly adapt to the behavior of previously unknown associates, who may themselves be learning. This machine-learning problem is particularly challenging due, in part, to the presence of…

Policy-Space Response Oracles (PSRO) is a general algorithmic framework for learning policies in multiagent systems by interleaving empirical game analysis with deep reinforcement learning (Deep RL). At each iteration, Deep RL is invoked to…

Traditional reinforcement learning and planning typically requires vast amounts of data and training to develop effective policies. In contrast, large language models (LLMs) exhibit strong generalization and zero-shot capabilities, but…

Dull, weak and nested solitaire games are important classes of parity games, capturing, among others, alternation-free mu-calculus and ECTL* model checking problems. These classes can be solved in polynomial time using dedicated algorithms.…

An automatic program that generates constant profit from the financial market is lucrative for every market practitioner. Recent advance in deep reinforcement learning provides a framework toward end-to-end training of such trading agent.…

Card game AI has always been a hot topic in the research of artificial intelligence. In recent years, complex card games such as Mahjong, DouDizhu and Texas Hold'em have been solved and the corresponding AI programs have reached the level…