Analysis of Vanilla Rolling Horizon Evolution Parameters in General Video Game Playing

2017 IEEE Congress on Evolutionary Computation (CEC)

Peŕez-Liebana

2017

Self Cite

While Monte Carlo Tree Search and closely related methods have dominated General Video Game Playing, recent research has demonstrated the promise of Rolling Horizon Evolutionary Algorithms as an interesting alternative. However, there is little attention paid to population initialization techniques in the setting of general real-time video games. Therefore, this paper proposes the use of population seeding to improve the performance of Rolling Horizon Evolution and presents the results of two methods, One Step Look Ahead and Monte Carlo Tree Search, tested on 20 games of the General Video Game AI corpus with multiple evolution parameter values (population size and individual length). An in-depth analysis is carried out between the results of the seeding methods and the vanilla Rolling Horizon Evolution. In addition, the paper presents a comparison to a Monte Carlo Tree Search algorithm. The results are promising, with seeding able to boost performance significantly over baseline evolution and even match the high level of play obtained by the Monte Carlo Tree Search.

Section: Resultsmentioning

confidence: 99%

“…The algorithm described in this subsection is the baseline used in the study and follows the same technique described in [23]. It employs a pseudo-random initialization of the population, each gene in the individuals taking on an integer value returned by an RNG (Random Number Generator).…”

Section: B Vanilla Rhea (Algorithm A-vanilla)mentioning

confidence: 99%

Population seeding techniques for Rolling Horizon Evolution in General Video Game Playing

Gaina

2017 IEEE Congress on Evolutionary Computation (CEC)

Peŕez-Liebana

2017

Self Cite

“…Both games are fairly similar in concept and difficulty for a vanilla RHEA agent (100% win-rate in both, first level only considered for Missile Command) [21]. However, their complexity in terms of local patterns does differ.…”

Section: Further Applicationsmentioning

confidence: 97%

A Local Approach to Forward Model Learning: Results on the Game of Life Game

2019 IEEE Conference on Games (CoG)

Dockhorn

Volz

et al. 2019

Self Cite

“…individual length, mutation rate), but also the very structure of the algorithm (keeping the population evolved from one game tick to the next with a shift buffer, including or excluding evolutionary operators, adding Monte Carlo rollouts at the end of the individual when evaluating, etc.). These options are all collected from past literature [23], [41], [44], [45] for a resulting EA with a parameter search space size of 1.741E12.…”

Section: B Planning Modulementioning

confidence: 99%

Project Thyia: A Forever Gameplayer

Gaina

2019 IEEE Conference on Games (CoG)

Peŕez-Liebana

2019

Self Cite

The space of Artificial Intelligence entities is dominated by conversational bots. Some of them fit in our pockets and we take them everywhere we go, or allow them to be a part of human homes. Siri, Alexa, they are recognised as present in our world. But a lot of games research is restricted to existing in the separate realm of software. We enter different worlds when playing games, but those worlds cease to exist once we quit. Similarly, AI game-players are run once on a game (or maybe for longer periods of time, in the case of learning algorithms which need some, still limited, period for training), and they cease to exist once the game ends. But what if they didn't? What if there existed artificial game-players that continuously played games, learned from their experiences and kept getting better? What if they interacted with the real world and us, humans: livestreaming games, chatting with viewers, accepting suggestions for strategies or games to play, forming opinions on popular game titles? In this paper, we introduce the vision behind a new project called Thyia, which focuses around creating a present, continuous, 'always-on', interactive game-player.