Optimizing Strategy Parameters in a Game Bot
نویسندگان
چکیده
This paper proposes an Evolutionary Algorithm for finetuning the behavior of a bot designed for playing Planet Wars, a game that has been selected for the the Google Artificial Intelligence Challenge 2010. The behavior engine of the proposed bot is based on a set of rules established by means of heuristic experimentation, followed by the application of an evolutionary algorithm to set the constants, weights and probabilities needed by those rules. This bot eventually defeated the baseline bot used to design it in most maps, and eventually played in the Google AI competition, obtaining a ranking in the top 20%.
منابع مشابه
Neuroticism - A Competitive Advantage (Also) for IVAs?
Real-Time Strategy (RTS) games are a challenging genre for the design of Intelligent Virtual Agents. We were interested whether incorporating a simple emotional model to an existing bot-script improves playing strength. We implemented a bot for Microsoft's RTS game “Age of Mythology”. The emotional model is based on the “Big-Five” and the Emotion-Connectionist Model. Four variants of the bot we...
متن کاملPavlov’s Arcade Reinforcement Learning for a Breakout AI
In this paper we describe the design and implementation of a bot to play the arcade game Breakout. Instead of manually writing the bot, we use reinforcement learning techniques to learn a strategy by repeated sessions of Breakout where the learner is rewarded for advancing through the game and punished for losing. We show that our bot’s game performance increases with repeated plays, though it ...
متن کاملLearning to Play Hearthstone Using Machine Learning
The subject of this thesis is a new game called Hearthstone. It is a strategy card game developed by Blizzard Entertainment, in which players duel with each other with cards they collected. The game of Hearthstone provides a challenge for developing an artificial intelligence (AI) agent. The agent has to be able to deal with unknown information and stochastic events in a large search space. In ...
متن کاملA Multi-Agent Potential Field-based Bot for a Full RTS Game Scenario
Computer games in general, and Real Time Strategy games in particular is a challenging task for both AI research and game AI programmers. The player, or AI bot, must use its workers to gather resources. They must be spent wisely on structures such as barracks or factories, mobile units such as soldiers, workers and tanks. The constructed units can be used to explore the game world, hunt down th...
متن کاملELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
In this paper, we propose ELF, an Extensive, Lightweight and Flexible platform for fundamental reinforcement learning research. Using ELF, we implement a highly customizable real-time strategy (RTS) engine with three game environments (Mini-RTS, Capture the Flag and Tower Defense). Mini-RTS, as a miniature version of StarCraft, captures key game dynamics and runs at 40K frame-persecond (FPS) pe...
متن کامل