English
Related papers

Related papers: Mastering Atari, Go, Chess and Shogi by Planning w…

200 papers

AlphaZero is a self-play reinforcement learning algorithm that achieves superhuman play in chess, shogi, and Go via policy iteration. To be an effective policy improvement operator, AlphaZero's search requires accurate value estimates for…

Artificial Intelligence · Computer Science 2023-03-02 Alexandre Trudeau , Michael Bowling

Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billions) of environment steps to train. Recently, there has been…

Machine Learning · Computer Science 2021-12-14 Weirui Ye , Shaohuai Liu , Thanard Kurutach , Pieter Abbeel , Yang Gao

In this paper, we explore and compare multiple algorithms for solving the complex strategy game of Terra Mystica, hereafter abbreviated as TM. Previous work in the area of super-human game-play using AI has proven effective, with recent…

Multiagent Systems · Computer Science 2021-02-23 Luis Perez

Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an opportunity to further human knowledge and improve human expert performance by leveraging…

Artificial Intelligence · Computer Science 2023-10-26 Lisa Schut , Nenad Tomasev , Tom McGrath , Demis Hassabis , Ulrich Paquet , Been Kim

Search and planning algorithms have been a cornerstone of artificial intelligence since the field's inception. Giving reinforcement learning agents the ability to plan during execution time has resulted in significant performance…

Artificial Intelligence · Computer Science 2023-12-05 Carlos Martin , Tuomas Sandholm

We propose a novel policy update that combines regularized policy optimization with model learning as an auxiliary loss. The update (henceforth Muesli) matches MuZero's state-of-the-art performance on Atari. Notably, Muesli does so without…

Recently, the seminal algorithms AlphaGo and AlphaZero have started a new era in game learning and deep reinforcement learning. While the achievements of AlphaGo and AlphaZero - playing Go and other complex games at super human level - are…

Machine Learning · Computer Science 2022-09-27 Johannes Scheiermann , Wolfgang Konen

Games are abstractions of the real world, where artificial agents learn to compete and cooperate with other agents. While significant achievements have been made in various perfect- and imperfect-information games, DouDizhu (a.k.a. Fighting…

Artificial Intelligence · Computer Science 2021-06-14 Daochen Zha , Jingru Xie , Wenye Ma , Sheng Zhang , Xiangru Lian , Xia Hu , Ji Liu

Tactical decision making for autonomous driving is challenging due to the diversity of environments, the uncertainty in the sensor information, and the complex interaction with other road users. This paper introduces a general framework for…

AlphaZero-type algorithms may stop improving on single-player tasks in case the value network guiding the tree search is unable to approximate the outcome of an episode sufficiently well. One technique to address this problem is…

Machine Learning · Computer Science 2023-06-08 Jonathan Pirnay , Quirin Göttl , Jakob Burger , Dominik Gerhard Grimm

AlphaZero, an approach to reinforcement learning that couples neural networks and Monte Carlo tree search (MCTS), has produced state-of-the-art strategies for traditional board games like chess, Go, shogi, and Hex. While researchers and…

Artificial Intelligence · Computer Science 2022-11-29 Charles Lovering , Jessica Zosa Forde , George Konidaris , Ellie Pavlick , Michael L. Littman

Game solving is a similar, yet more difficult task than mastering a game. Solving a game typically means to find the game-theoretic value (outcome given optimal play), and optionally a full strategy to follow in order to achieve that…

Artificial Intelligence · Computer Science 2023-11-14 Ti-Rong Wu , Hung Guei , Ting Han Wei , Chung-Chin Shih , Jui-Te Chin , I-Chen Wu

In 2019, Google DeepMind released MuZero, a model-based reinforcement learning method that achieves strong results in perfect-information games by combining learned dynamics models with Monte Carlo Tree Search (MCTS). However, comparatively…

Artificial Intelligence · Computer Science 2026-03-31 Adam Haile

Deep reinforcement learning repeatedly succeeds in closed, well-defined domains such as games (Chess, Go, StarCraft). The next frontier is real-world scenarios, where setups are numerous and varied. For this, agents need to learn the…

Machine Learning · Computer Science 2023-02-10 Andreea Deac , Théophane Weber , George Papamakarios

It is non-trivial to design engaging and balanced sets of game rules. Modern chess has evolved over centuries, but without a similar recourse to history, the consequences of rule changes to game dynamics are difficult to predict. AlphaZero…

Artificial Intelligence · Computer Science 2020-09-16 Nenad Tomašev , Ulrich Paquet , Demis Hassabis , Vladimir Kramnik

The success of AlphaZero (AZ) has demonstrated that neural-network-based Go AIs can surpass human performance by a large margin. Given that the state space of Go is extremely large and a human player can play the game from any legal state,…

Artificial Intelligence · Computer Science 2022-11-08 Li-Cheng Lan , Huan Zhang , Ti-Rong Wu , Meng-Yu Tsai , I-Chen Wu , Cho-Jui Hsieh

Complex sequential decision-making planning problems, covering infinite states' space have been shown to be solvable by AlphaZero type of algorithms. Such an approach that trains a neural model while simulating projection of futures with a…

Artificial Intelligence · Computer Science 2024-08-13 Ronit Bustin , Claudia V. Goldman

Building agents based on tree-search planning capabilities with learned models has achieved remarkable success in classic decision-making problems, such as Go and Atari. However, it has been deemed challenging or even infeasible to extend…

Machine Learning · Computer Science 2023-10-13 Yazhe Niu , Yuan Pu , Zhenjie Yang , Xueyan Li , Tong Zhou , Jiyuan Ren , Shuai Hu , Hongsheng Li , Yu Liu

This paper uses chess, a landmark planning problem in AI, to assess transformers' performance on a planning task where memorization is futile $\unicode{x2013}$ even at a large scale. To this end, we release ChessBench, a large-scale…

Recent breakthroughs in Artificial Intelligence have shown that the combination of tree-based planning with deep learning can lead to superior performance. We present Adaptive Entropy Tree Search (ANTS) - a novel algorithm combining…

Artificial Intelligence · Computer Science 2023-03-16 Piotr Kozakowski , Mikołaj Pacek , Piotr Miłoś