Automatically Reinforcing a Game AI
A recent research trend in Artificial Intelligence (AI) is the combination of several programs into one single, stronger, program; this is termed portfolio methods. We here investigate the application of such methods to Game Playing Programs (GPPs). In addition, we consider the case in which only one GPP is available - by decomposing this single GPP into several ones through the use of parameters or even simply random seeds. These portfolio methods are trained in a learning phase. We propose two different offline approaches. The simplest one, BestArm, is a straightforward optimization of seeds or parame- ters; it performs quite well against the original GPP, but performs poorly against an opponent which repeats games and learns. The second one, namely Nash-portfolio, performs similarly in a "one game" test, and is much more robust against an opponent who learns. We also propose an online learning portfolio, which tests several of the GPP repeatedly and progressively switches to the best one - using a bandit algorithm.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Augmenting Automated Game Testing with Deep Reinforcement Learning
General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-lear…
Deep Reinforcement LearningFPS Gamesreinforcement-learningReinforcement Learning+2Developing for personalised learning: the long road from educational objectives to development and feedback
This paper describes the development needed to support the functional and teaching requirements of iRead, a 4-year EU-funded project which produced an award-winning serious game utilising lexical and syntactical game con…
Language ModelingLanguage ModellingMulti-agent KTO: Reinforcing Strategic Interactions of Large Language Model in Language Game
Achieving Artificial General Intelligence (AGI) requires AI agents that can not only make stratigic decisions but also engage in flexible and meaningful communication. Inspired by Wittgenstein's language game theory in P…
Decision MakingLanguage ModelingLanguage ModellingLarge Language Model+1Automatically Detecting Cyberbullying Comments on Online Game Forums
Online game forums are popular to most of game players. They use it to communicate and discuss the strategy of the game, or even to make friends. However, game forums also contain abusive and harassment speech, disturbin…
Reinforcing Competitive Multi-Agents for Playing So Long Sucker
This paper examines the use of classical deep reinforcement learning (DRL) algorithms, DQN, DDQN, and Dueling DQN, in the strategy game So Long Sucker (SLS), a diplomacy-driven game defined by coalition-building and stra…
BenchmarkingDeep Reinforcement Learning