Procedural Play Generation According to Play Arcs Using Monte-Carlo Tree Search
نویسندگان
چکیده
More than a million spectators watch game streaming platforms such as Twitch every month. This phenomenon suggests video games are a powerful entertainment media not just for players but for spectators as well. Since each spectator has personal preferences, customized spectator-specific game plays are arguably a promising option to increase the entertainment value of video games streaming. In this paper, we propose an Artificial Intelligence (AI) that automatically generates game plays according to play arcs using Monte Carlo Tree Search (MCTS). In particular, we concentrate on fighting games and drive MCTS to achieve specific hitpoints differences between characters at different moments of the game. Our preliminary results show that the proposed AI can generate game plays following the desired transition of game progress.
منابع مشابه
Automated Playtesting with Procedural Personas through MCTS with Evolved Heuristics
This paper describes a method for generative player modeling and its application to the automatic testing of game content using archetypal player models called procedural personas. Theoretically grounded in psychological decision theory, procedural personas are implemented using a variation of Monte Carlo Tree Search (MCTS) where the node selection criteria are developed using evolutionary comp...
متن کاملProcedural Content Generation of Angry Birds Levels Using Monte Carlo Tree Search APPROVED BY SUPERVISING COMMITTEE:
متن کامل
Generating Sokoban Puzzle Game Levels with Monte Carlo Tree Search
In this work, we develop a Monte Carlo Tree Search based approach to procedurally generate Sokoban puzzles. To this end, we propose heuristic metrics based on surrounding box path congestion and level tile layout to guide the search towards interesting puzzles. Our method generates puzzles through simulated game play, guaranteeing solvability in all generated puzzles. Our algorithm is efficient...
متن کاملTechnical Reports Cover
In this work, we develop a Monte Carlo Tree Search based approach to procedurally generate Sokoban puzzles. To this end, we propose heuristic metrics based on surrounding box path congestion and level tile layout to guide the search towards interesting puzzles. Our method generates puzzles through simulated game play, guaranteeing solvability in all generated puzzles. Our algorithm is efficient...
متن کاملMonte-Carlo Tree Search for Persona Based Player Modeling
Is it possible to conduct player modeling without any players? In this paper we use Monte-Carlo Tree Search-controlled procedural personas to simulate a range of decision making styles in the puzzle game MiniDungeons 2. The purpose is to provide a method for synthetic play testing of game levels with synthetic players based on designer intuition and experience. Five personas are constructed, re...
متن کامل