MCTS/UCT in Solving Real-Life Problems

Mańdziuk, Jacek

doi:10.1007/978-3-319-67946-4_11

Cited by 5 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The MCTS as a general-purpose heuristic decision algorithm also has many applications outside the world of games. These include combinatorial optimization, scheduling tasks, sample-based planning, and procedural content generation [4], [16]. More recently, domain of usage has been expanded to material design [14], network optimisation [13], multi-robot active perception [1], cryptography [8] and others [12], [20].…”

Section: Introductionmentioning

confidence: 99%

Optimisation of MCTS Player for The Lord of the Rings: The Card Game

Godlewski,

Sawicki

2021

Preprint

View full text Add to dashboard Cite

The article presents research on the use of Monte-Carlo Tree Search (MCTS) methods to create an artificial player for the popular card game "The Lord of the Rings". The game is characterized by complicated rules, multi-stage round construction, and a high level of randomness. The described study found that the best probability of a win is received for a strategy combining expert knowledge-based agents with MCTS agents at different decision stages. It is also beneficial to replace random playouts with playouts using expert knowledge. The results of the final experiments indicate that the relative effectiveness of the developed solution grows as the difficulty of the game increases.

show abstract

Section: Introductionmentioning

confidence: 99%

Optimisation of MCTS Player for The Lord of the Rings: The Card Game

Godlewski,

Sawicki

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The MCTS as a general purpose heuristic decision algorithm has also many applications outside the world of games. These include combinatorial optimization, scheduling tasks, sample-based planning, and procedural content generation [1,4]. More recently, domain of usage is expanding to material design [5], network optimisation [6], multi-robot active perception [7], cryptography [8] and others [9,10].…”

Section: Introductionmentioning

confidence: 99%

Bulletin of the Polish Academy of Sciences: Technical Sciences

Godlewski

Sawicki

2021

View full text Add to dashboard Cite

they are an effective, modern educational tool [13], e.g., in medicine [14]. Cooperation allows to learn teamwork, and this is often not possible without the additional presence of artificial players with decision making skills. The main difficulty in cooperative games is created by a complex, multi-stage round structure, which contains several unpredictable random events. Cooperative games make it also possible to play solo, which was analysed in this research.An interesting approach for MCTS application in collectible card games has been presented in 2019 using the "Hearthstone" game [15]. Authors identified huge size of the action space. Several precautions had been taken to reduce number of allowed moves. Using Action filtering and Obliged Actions are examples of successful domain-specific knowledge incorporation.This article is directly based on authors conference work [16]. The algorithm has been extended by adding more expert knowledge into the standard MCTS implementation. This allowed to perform a new analysis for games with high complexity level. We have demonstrated that the relative effectiveness of the mixed strategy proposed in [16] rises as the difficulty of the problem increases. The Lord of the Rings: The Card Game"The Lord of the Rings: The Card Game", often abbreviated as LoTR, is a complicated cooperative card game with several decision-making stages. The following section is devoted to the presentation of its basic rules. It is necessary to understand before we will discuss construction of the game simulator, and searching for the optimal strategy for the AI player. Living Card Game.From the Poker to the "Magic: the Gathering", card games belong to a group of games characterized by hidden information and a high degree of randomness. Hidden information means that the player does not have a complete view of the game, opposing cards

show abstract

“…The direction is chosen randomly but the distance is drawn from a stable distribution [14]: Although Monte Carlo Tree Search is most often applied to games, its foundation is in decision theory. It is beginning to be applied to a much wider array of problems [11]. A similar application of MCTS to the search detection scenario described above is called the multi-armed bandit problem [1,8].…”

Section: Introductionmentioning

confidence: 99%

Monte Carlo Tree Search for a single target search game on a 2-D lattice

Kozak,

Hottovy

2020

Preprint

View full text Add to dashboard Cite

Monte Carlo Tree Search (MCTS) is a branch of stochastic modeling that utilizes decision trees for optimization, mostly applied to artificial intelligence (AI) game players. This project imagines a ?game? in which an AI player searches for a stationary target within a 2-D lattice. We analyze its behavior with different target distributions and compare its efficiency to the Levy Flight Search, a model for animal foraging behavior. In addition to simulated data analysis we prove two theorems about the convergence of MCTS when computation constraints disappear.

show abstract

MCTS/UCT in Solving Real-Life Problems

Cited by 5 publications

References 27 publications

Optimisation of MCTS Player for The Lord of the Rings: The Card Game

Optimisation of MCTS Player for The Lord of the Rings: The Card Game

Bulletin of the Polish Academy of Sciences: Technical Sciences

Monte Carlo Tree Search for a single target search game on a 2-D lattice

Contact Info

Product

Resources

About