Monte Carlo Tree Search: A Review of Recent Modifications and Applications

Świechowski, Maciej; Godlewski, Konrad; Sawicki, Bartosz; Mańdziuk, Jacek

doi:10.48550/arxiv.2103.04931

Cited by 6 publications

(7 citation statements)

References 132 publications

(149 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Monte Carlo Tree Search (MCTS) is a stochastic, anytime, asymmetric, knowledge-free search algorithm popular in a wide range of games and non-games problems (Browne et al, 2012;Świechowski et al, 2021). It has been especially successful in the domains of computer Go (Silver et al, 2016) and various challenges of General Game Playing (Perez-Liebana et al, 2019b;Finnsson and Björnsson, 2010).…”

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

Developing a Successful Bomberman Agent

Kowalczyk

Kowalski

Obrzut

et al. 2022

Proceedings of the 14th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

In this paper, we study AI approaches to successfully play a 2-4 players, full information, Bomberman variant published on the CodinGame platform. We compare the behavior of three search algorithms: Monte Carlo Tree Search, Rolling Horizon Evolution, and Beam Search. We present various enhancements leading to improve the agents' strength that concern search, opponent prediction, game state evaluation, and game engine encoding. Our top agent variant is based on a Beam Search with low-level bit-based state representation and evaluation function heavy relying on pruning unpromising states based on simulation-based estimation of survival. It reached the top one position among the 2,300 AI agents submitted on the CodinGame arena.

show abstract

Section: Monte Carlo Tree Searchmentioning

confidence: 99%

Developing a Successful Bomberman Agent

Kowalczyk

Kowalski

Obrzut

et al. 2022

Proceedings of the 14th International Conference on Agents and Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…The plan relies on a smart tree search that balances exploration and exploitation. Random sampling is employed in MCTS in the form of simulations to save statistics of activities and make more knowledgeable selections in each future iteration [72]. MCTS is a decision-making technique that is utilized in scanning huge combinatorial spaces represented by trees.…”

Section: B Monte Carlo Tree Searchmentioning

confidence: 99%

“…MCTS is a decision-making technique that is utilized in scanning huge combinatorial spaces represented by trees. In such trees, nodes represent states, also referred to as con gurations of the problem, whereas edges denote transitions (actions) between states [72].…”

Section: B Monte Carlo Tree Searchmentioning

confidence: 99%

Artificial Intelligence-Based Traffic Flow Prediction: A Comprehensive Review

Sayed

Abdelhamid

Hefny

2022

Preprint

View full text Add to dashboard Cite

The expansion of the Internet of Things has resulted in new creative solutions, such as smart cities, that have made our lives more productive, convenient, and intelligent. The core of smart cities is the Intelligent Transportation System (ITS) which has been integrated into several smart city applications that improve transportation and mobility. ITS aims to resolve traffic issues, especially traffic congestion. Recently, new traffic flow prediction models and frameworks have been rapidly developed in tandem with the introduction of Artificial Intelligence (AI) approaches to improve the accuracy of traffic flow prediction. Traffic forecasting is a crucial duty in the transportation industry. It can significantly affect the design of road constructions and projects in addition to its importance for route planning and traffic rules. Furthermore, traffic congestion is a critical issue in urban areas and overcrowded cities. Therefore, it must be accurately evaluated and forecasted. Hence, a reliable and efficient method for predicting traffic is essential. The main objectives of this study are: First, present a comprehensive review of the most popular machine learning and deep learning techniques applied in traffic prediction. Second, identifying inherent obstacles to applying machine learning and deep learning in the domain of traffic prediction.

show abstract

“…They are DESs with larger branching factors, which results that agents usually have not sufficient time to make decisions. One of the main bottlenecks of algorithms in such complex environments is that search spaces are too huge [1].…”

Section: Introductionmentioning

confidence: 99%

ImS-MCTS: A New Importance Sampling MCTS Algorithm for Discrete Event System

Ou,

Lu,

Wang

et al. 2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

With the emergence of a discrete event system (DES), the research community is developing in the direction of various issues within it. In this kind of system, the decision-making problem is one of the core issues. In this paper, we build a new decision-making algorithm ImS-MCTS based on Monte Carlo Tree Search (MCTS). As for decision-making problems, MCTS family is a state-of-the-art kind of algorithms, this kind of algorithm can be decomposed into tree search and Monte Carlo (MC) method. The MC method approximates the value function of the current state by simulating future states. Researchers face the challenge of capturing rare events during simulation to make accurate estimations, resulting in a huge number of samples being required, which is often impractical in reality. To solve this problem, we propose ImS-MCTS to improve the traditional MC method through importance sampling. The improvement reduces the sampling frequency of non-rare events by probability mapping, effectively reduces the sample space, and helps tree search compute more efficiently. We design experiments in autonomous driving. The results show that: compared with traditional MCTS methods, ImS-MCTS can improve the success rate of collision avoidance by about 7.12% and reduce the time cost by about 6.24% in the test road section, which indicates that ImS-MCTS makes better decisions.

show abstract

Monte Carlo Tree Search: A Review of Recent Modifications and Applications

Cited by 6 publications

References 132 publications

Developing a Successful Bomberman Agent

Developing a Successful Bomberman Agent

Artificial Intelligence-Based Traffic Flow Prediction: A Comprehensive Review

ImS-MCTS: A New Importance Sampling MCTS Algorithm for Discrete Event System

Contact Info

Product

Resources

About