Evolving Game-Specific UCB Alternatives for General Video Game Playing

Bravi, Ivan; Khalifa, Ahmed; Holmgård, Christoffer; Togelius, Julian

doi:10.1007/978-3-319-55849-3_26

Cited by 16 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a different study, Khalifa et al [31] applied multi-objective concepts to evolving parameters for a tree selection confidence bounds equation. A previous work by Bravi [32] (also discussed in Section IV-D) provided multiple UCB equations for different games. The work in [31] evolved, using S-Metric Selection Evolutionary Multi-objective Optimization Algorithm (SMS-EMOA), the linear weights of a UCB equation that results of combining all from [32] in a single one.…”

Section: B Tree Search Methodsmentioning

confidence: 99%

“…Evolution and MCTS have also been combined in different ways. In one of them, Bravi et al [49] used a GP system to evolve different tree policies for MCTS. Concretely, the authors evolve a different policy for each one of the 5 games employed in the study, aiming to exploit the characteristics of each game in particular.…”

Section: Hybridsmentioning

confidence: 99%

“…Primary results showed that one of the studied agents achieved a similar distribution of repeated actions to the one by human players. The work was then extended by Bravi et al [49], in which game-play data have been used to evolve effective UCT alternatives for a specific game. The MCTS agents using new formulas, with none or limited domain information, are compared to a standard implementation of MCTS (the sampleMCTS agent of GVGAI) on the game Missile Command.…”

Section: B Ai-assisted Game Designmentioning

confidence: 99%

See 2 more Smart Citations

General Video Game AI: A Multitrack Framework for Evaluating Agents, Games, and Content Generation Algorithms

et al. 2019

Self Cite

View full text Add to dashboard Cite

General Video Game Playing (GVGP) aims at designing an agent that is capable of playing multiple video games with no human intervention. In 2014, The General Video Game AI (GVGAI) competition framework was created and released with the purpose of providing researchers a common open-source and easy to use platform for testing their AI methods with potentially infinity of games created using Video Game Description Language (VGDL). The framework has been expanded into several tracks during the last few years to meet the demand of different research directions. The agents are required either to play multiple unknown games with or without access to game simulations, or to design new game levels or rules. This survey paper presents the VGDL, the GVGAI framework, existing tracks, and reviews the wide use of GVGAI framework in research, education and competitions five years after its birth. A future plan of framework improvements is also described.

show abstract

Section: B Tree Search Methodsmentioning

confidence: 99%

Section: Hybridsmentioning

confidence: 99%

Section: B Ai-assisted Game Designmentioning

confidence: 99%

See 1 more Smart Citation

General Video Game AI: A Multitrack Framework for Evaluating Agents, Games, and Content Generation Algorithms

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, Bravi el al. [19] custom various heuristics particularly for some GVGAI games, and Sironi el al. [20] design several Self-Adaptive MCTS variants which use hyperparameter optimisation methods to tune on-line the exploration factor and maximal roll-out depth during the game playing.…”

Section: B Monte Carlo Tree Search-based Agentsmentioning

confidence: 99%

“…In this work, each pair of agents is tested over 20 playthroughs The GPMCTS agent is an MCTS agent with customisable Tree Policy as described in [19].…”

Section: Experimental Set-upmentioning

confidence: 99%

Shallow Decision-Making Analysis in General Video Game Playing

Bravi

Peŕez-Liebana

Lucas

et al. 2018

2018 IEEE Conference on Computational Intelligence and Games (CIG)

Self Cite

View full text Add to dashboard Cite

The General Video Game AI competitions have been the testing ground for several techniques for game-playing, such as evolutionary computation techniques, tree search algorithms, hyper-heuristic-based or knowledge-based algorithms. So far the metrics used to evaluate the performance of agents have been win ratio, game score and length of games. In this paper we provide a wider set of metrics and a comparison method for evaluating and comparing agents. The metrics and the comparison method give shallow introspection into the agent's decision-making process and they can be applied to any agent regardless of its algorithmic nature. In this work, the metrics and the comparison method are used to measure the impact of the terms that compose a tree policy of an MCTS-based agent, comparing with several baseline agents. The results clearly show how promising such general approach is and how it can be useful to understand the behaviour of an AI agent, in particular, how the comparison with baseline agents can help understanding the shape of the agent decision landscape. The presented metrics and comparison method represent a step toward to more descriptive ways of logging and analysing agent's behaviours.

show abstract

Multi-objective Adaptation of a Parameterized GVGAI Agent Towards Several Games

Khalifa

Preuß

Togelius

2017

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

This paper proposes a benchmark for multi-objective optimization based on video game playing. The challenge is to optimize an agent to perform well on several different games, where each objective score corresponds to the performance on a different game. The benchmark is inspired from the quest for general intelligence in the form of general game playing, and builds on the General Video Game AI (GV-GAI) framework. As it is based on game-playing, this benchmark incorporates salient aspects of game-playing problems such as discontinuous feedback and a non-trivial amount of stochasticity. We argue that the proposed benchmark thus provides a different challenge from many other benchmarks for multi-objective optimization algorithms currently available. We also provide initial results on categorizing the space offered by this benchmark and applying a standard multi-objective optimization algorithm to it.

show abstract

Evolving Game-Specific UCB Alternatives for General Video Game Playing

Cited by 16 publications

References 18 publications

General Video Game AI: A Multitrack Framework for Evaluating Agents, Games, and Content Generation Algorithms

General Video Game AI: A Multitrack Framework for Evaluating Agents, Games, and Content Generation Algorithms

Shallow Decision-Making Analysis in General Video Game Playing

Multi-objective Adaptation of a Parameterized GVGAI Agent Towards Several Games

Contact Info

Product

Resources

About