Level generation for angry birds with sequential VAE and latent variable evolution

Video game level generation based on machine learning (ML), in particular, deep generative models, has attracted attention as a technique to automate level generation. However, applications of existing ML-based level generations are mostly limited to tile-based level representation. When ML techniques are applied to game domains with non-tile-based level representation, such as Angry Birds, where objects in a level are specified by real-valued parameters, ML often fails to generate playable levels. In this study, we develop a deep-generative-model-based level generation for the game domain of Angry Birds. To overcome these drawbacks, we propose a sequential encoding of a level and process it as text data, whereas existing approaches employ a tile-based encoding and process it as an image. Experiments show that the proposed level generator drastically improves the stability and diversity of generated levels compared with existing approaches. We apply latent variable evolution with the proposed generator to control the feature of a generated level computed through an AI agent's play, while keeping the level stable and natural.

[1]  Claudio Fabiano Motta Toledo,et al.  A search-based approach for generating Angry Birds levels , 2014, 2014 IEEE Conference on Computational Intelligence and Games.

[2]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[3]  Alexander M. Rush,et al.  Character-Aware Neural Language Models , 2015, AAAI.

[4]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[5]  Jochen Renz,et al.  Generating varied, stable and solvable levels for angry birds style physics games , 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG).

[6]  Julian Togelius,et al.  Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation , 2018, 1806.10729.

[7]  Nikolaus Hansen,et al.  Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation , 1996, Proceedings of IEEE International Conference on Evolutionary Computation.

[8]  Julian Togelius,et al.  Deep learning for procedural content generation , 2020, Neural Computing and Applications.

[9]  Julian Togelius,et al.  Procedural Content Generation via Machine Learning (PCGML) , 2017, IEEE Transactions on Games.

[10]  Adeel Zafar,et al.  Corpus for Angry Birds Level Generation , 2019, 2019 2nd International Conference on Computing, Mathematics and Engineering Technologies (iCoMET).

[11]  Colin Raffel,et al.  A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music , 2018, ICML.

[12]  Samy Bengio,et al.  Generating Sentences from a Continuous Space , 2015, CoNLL.

[13]  Julian Togelius,et al.  Linear levels through n-grams , 2014, MindTrek.

[14]  Edoardo Giacomello,et al.  Searching the Latent Space of a Generative Adversarial Network to Generate DOOM Levels , 2019, 2019 IEEE Conference on Games (CoG).

[15]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[16]  Simon M. Lucas,et al.  Evolving mario levels in the latent space of a deep convolutional generative adversarial network , 2018, GECCO.

[17]  Petros Koumoutsakos,et al.  Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES) , 2003, Evolutionary Computation.

[18]  Alexandru Iosup,et al.  Procedural content generation for games: A survey , 2013, TOMCCAP.

[19]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[20]  Taehoon Kim,et al.  Quantifying Generalization in Reinforcement Learning , 2018, ICML.

[21]  Julian Togelius,et al.  The 2017 AIBIRDS Level Generation Competition , 2019, IEEE Transactions on Games.

[22]  Pujana Paliyawan,et al.  Generating Angry Birds-Like Levels With Domino Effects Using Constrained Novelty Search , 2020, 2020 IEEE Conference on Games (CoG).

[23]  Julian Togelius,et al.  Autoencoder and Evolutionary Algorithm for Level Generation in Lode Runner , 2019, 2019 IEEE Conference on Games (CoG).

[24]  Matthew Guzdial,et al.  Game Level Generation from Gameplay Videos , 2021, AIIDE.

[25]  Julian Togelius,et al.  Bootstrapping Conditional GANs for Video Game Level Generation , 2019, 2020 IEEE Conference on Games (CoG).

[26]  Jochen Renz,et al.  Agent-Based Adaptive Level Generation for Dynamic Difficulty Adjustment in Angry Birds , 2019, ArXiv.