Predicting Player Experience without the Player.

Guckelsberger, Christian; Salge, Christoph; Gow, Jeremy; Cairns, Paul

doi:10.1145/3116595.3116631

Cited by 29 publications

(29 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[63], for instance, takes a Monte-Carlo approach to evaluating diversity and playability by observing the scores of a large number of simple AI players. In contrast, [126] and [46] apply models of game experience that originate from related research, namely the concepts of flow and empowerment. In [46], the employed model is also verified using explicit quantitative and qualitative feedback from human players.…”

Section: A22 Platformersmentioning

confidence: 99%

Uncertainty Handling in Surrogate Assisted Optimisation of Games

Volz

2019

Künstl Intell

View full text Add to dashboard Cite

A detailed illustrative example of how modelling human players using AIs can bias the obtained outcomes based on published data for the game StarCraft II (Blizzard 2010). The example conclusively shows the need for uncertainty handling in simulation-based game-related optimisation.The example is based on an algorithm for StarCraft II winner prediction as published in [VPB18] with my co-authors Mike Preuss and Mathias K. Bonde. The analysis presented in this paper was however not published yet and is based on newly generated results from different datasets. The example also profited from discussion with Boris Naujoks. CHAPTER 1. INTRODUCTION Game-Benchmark for Evolutionary AlgorithmsAn extension of the existing COCO benchmarking framework for numerical black-box optimisation 3 that introduces two new functions suites based on game optimisation problems. The benchmark code, results and further information is freely available 4 . Two workshops around the benchmark were also organised for GECCO 2018 and 2019 in collaboration with Tea Tušar, Boris Naujoks and Pascal Kerschke. The interface for the new functions to the existing framework was implemented by Tea Tušar.The new function suites are based on two previous publications. The first is an optimisation problem for cards in TopTrumps that was introduced to demonstrate the feasibility of automatic game balancing with and without surrogate models in collaboration with Boris Naujoks and Günter Rudolph in [VRN16]. The second function suite is based on a significantly extended version of a procedural content generation technique for Super Mario Bros. levels proposed in [Vol+18] developed with SAPEO Algorithm SAPEO, an algorithm designed for the robust optimisation of games and similar complex simulation-based real-world problems. The algorithm is extensively evaluated theoretically and empirically. Benchmarks on artificial functions do attest SAPEO robust performance, especially for complex functions. However, we were not able to obtain a meaningful interpretation of the algorithm's performance on the game benchmark.Previous versions of SAPEO have been published for both single-and multi-objective optimisation problems in [VRN17a] and [VRN17b] in collaboration with Günter Rudolph and Boris Naujoks 6 . The version of SAPEO proposed in this thesis is however improved based on findings from previous publications and extended by model validation features as suggested by Alma Rahat. The results presented in this thesis are thus novel and not previously published. The theoretical performance assessment was supported by Michael Emmerich in context of a short term scientific mission 7 .

show abstract

Section: A22 Platformersmentioning

confidence: 99%

Uncertainty Handling in Surrogate Assisted Optimisation of Games

Volz

2019

Künstl Intell

View full text Add to dashboard Cite

show abstract

“…Our focus here is on algorithmic player modeling, i.e., approaches that explicitly implement behavioral laws and do not need extensive datasets, except possibly for parameter tuning. Such approaches offer greater flexibility of deployment, especially regarding automated testing and balancing of new games or game features for which data from human players is not yet available [24]. For a broader review of player modeling and the use of AI techniques in player modeling, we refer the reader to the work of Yannakakis and Togelius [93,94,95].…”

Section: A Note On Scopementioning

confidence: 99%

“…In summary, the excluded papers 1) did not propose or test any computational motivation model that can be implemented in a game-playing agent, or 2) used data-driven models that cannot necessarily be reapplied when game parameters change without collecting new data from human players [24]. On the other hand, we included papers that focus on non-player characters (NPCs) instead of simulated players; if such NPCs can generate plausible human-like behavior, the underlying techniques should be relevant for player modeling as well.…”

Section: A Note On Scopementioning

confidence: 99%

“…Found papers Included papers "player modeling" and "intrinsic motivation" 69 [11] "player modeling" and "competence" 132 [51,55,11] "player modeling" and "autonomy" 147 [11] "player modeling" and "relatedness" 23 [11] "player modeling" and "curiosity" 136 [27,11,53,65,25] "artificial intelligence" and "game testing" and "intrinsic motivation" 37 [20] "artificial intelligence" and "game testing" and "competence" 76 [20] "artificial intelligence" and "game testing" and "autonomy" 41 [20] "artificial intelligence" and "game testing" and "relatedness" 10 0 "artificial intelligence" and "game testing" and "curiosity" 78 [20] "player experience" and "intrinsic motivation" and "computational model" 32 [24,50] "player experience" and "competence" and "computational model" 53 [14,3,51,55,24,50] "player experience" and "autonomy" and "computational model" 48 [24] "player experience" and "relatedness" and "computational model" 11 [23,24] "player experience" and "curiosity" and "computational model" 51 [24,53,50] In addition to the explicit, algorithmic motivation models reviewed in this paper, simulated player agents can also utilize implicit, data-based models learned from real players. For example, the state-dependent probabilities of actions observed in real players have been included in the upper confidence bound (UCB) formula of Monte Carlo tree search [17,38].…”

Section: Searched Termsmentioning

confidence: 99%

See 1 more Smart Citation

Review of Intrinsic Motivation in Simulation-based Game Testing

Roohi

Takatalo

Guckelsberger

et al. 2018

Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

This paper presents a review of intrinsic motivation in player modeling, with a focus on simulation-based game testing. Modern AI agents can learn to win many games; from a game testing perspective, a remaining research problem is how to model the aspects of human player behavior not explained by purely rational and goal-driven decision making. A major piece of this puzzle is constituted by intrinsic motivations, i.e., psychological needs that drive behavior without extrinsic reinforcement such as game score. We first review the common intrinsic motivations discussed in player psychology research and artificial intelligence, and then proceed to systematically review how the various motivations have been implemented in simulated player agents. Our work reveals that although motivations such as competence and curiosity have been studied in AI, work on utilizing them in simulation-based game testing is sparse, and other motivations such as social relatedness, immersion, and domination appear particularly underexplored.

show abstract

“…Finally, there is also the question to which extent a player's empowerment in a game can be used as predictor for their experience. A preliminary study [5] identified causal efficacy as potential candidate experience that empowerment is closely related to, with mediate effects on "challenge, involvement, attention and engagement, learning and emotions". Having a measure that computes user experience without an actual player would be beneficial in rapid prototyping and when creating or adapting games automatically.…”

Section: A Motivationmentioning

confidence: 99%

Accelerating Empowerment Computation with UCT Tree Search

Salge

Guckelsberger

Canaan

et al. 2018

2018 IEEE Conference on Computational Intelligence and Games (CIG)

Self Cite

View full text Add to dashboard Cite

Models of intrinsic motivation present an important means to produce sensible behaviour in the absence of extrinsic rewards. Applications in video games are varied, and range from intrinsically motivated general game-playing agents to non-player characters such as companions and enemies. The information-theoretic quantity of Empowerment is a particularly promising candidate motivation to produce believable, generic and robust behaviour. However, while it can be used in the absence of external reward functions that would need to be crafted and learned, empowerment is computationally expensive. In this paper, we propose a modified UCT tree search method to mitigate empowerment's computational complexity in discrete and deterministic scenarios. We demonstrate how to modify a Monte-Carlo Search Tree with UCT to realise empowerment maximisation, and discuss three additional modifications that facilitate better sampling. We evaluate the approach both quantitatively, by analysing how close our approach gets to the baseline of exhaustive empowerment computation with varying amounts of computational resources, and qualitatively, by analysing the resulting behaviour in a Minecraft-like scenario.

show abstract

Predicting Player Experience without the Player.

Cited by 29 publications

References 43 publications

Uncertainty Handling in Surrogate Assisted Optimisation of Games

Uncertainty Handling in Surrogate Assisted Optimisation of Games

Review of Intrinsic Motivation in Simulation-based Game Testing

Accelerating Empowerment Computation with UCT Tree Search

Contact Info

Product

Resources

About