Fetching the paper…

Reading the bibliography…

2021

Adversarial Reinforcement Learning for Procedural Content Generation

Gisslén, Linus, Eakins, Andy, Gordillo, Camilo et al.

Original
PDF
Post on X

Understand

We present a new approach ARLPCG: Adversarial Reinforcement Learning for Procedural Content Generation, which procedurally generates and tests previously unseen environments with an auxiliary input as a control variable.

Training RL agents over novel environments is a notoriously difficult task.
One popular approach is to procedurally generate different environments to increase the generalizability of the trained agents.
ARLPCG instead deploys an adversarial model with one PCG RL agent (called Generator) and one solving RL agent (called Solver).

Adversarial Reinforcement Learning for Procedural Content Generation · Around

Built on

M. L. Littman and C. Szepesvári, “A generalized reinforcement-learning model: Convergence and applications,” in ICML , vol. 96. Citeseer, 1996, pp. 310–318
Original
1996
Earlier work this paper cites.
W. Uther and M. Veloso, “Adversarial reinforcement learning,” Tech. rep., Carnegie Mellon University. Unpublished, Tech. Rep., 1997
1997
Earlier work this paper cites.
I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” arXiv preprint arXiv:1406.2661 , 2014
Original
2014
Earlier work this paper cites.
M. Jaderberg, V. Mnih, W. M. Czarnecki, T. Schaul, J. Z. Leibo, D. Silver, and K. Kavukcuoglu, “Reinforcement learning with unsupervised auxiliary tasks,” arXiv preprint arXiv:1611.05397 , 2016
Original
2016
Earlier work this paper cites.
A. M. Connor, T. J. Greig, and J. Kruse, “Evaluating the impact of procedurally generated content on game immersion,” The Computer Games Journal , vol. 6, no. 4, pp. 209–225, 2017
2017
Earlier work this paper cites.
L. Pinto, J. Davidson, R. Sukthankar, and A. Gupta, “Robust adversarial reinforcement learning,” arXiv preprint arXiv:1703.02702 , 2017
Original
2017
Earlier work this paper cites.
C. Packer, K. Gao, J. Kos, P. Krähenbühl, V. Koltun, and D. Song, “Assessing generalization in deep reinforcement learning,” arXiv preprint arXiv:1810.12282 , 2018
Original
2018
Earlier work this paper cites.

Similar

J. Harmer, L. Gisslén, J. del Val, H. Holst, J. Bergdahl, T. Olsson, K. Sjöö, and M. Nordin, “Imitation learning with concurrent actions in 3d games,” in 2018 IEEE Conference on Computational Intelligence and Games (CIG) , 2018, pp. 1–8
2018
Cited alongside, same era.
N. Justesen, R. R. Torrado, P. Bontrager, A. Khalifa, J. Togelius, and S. Risi, “Illuminating generalization in deep reinforcement learning through procedural level generation,” arXiv preprint arXiv:1806.10729 , 2018
Original
2018
Cited alongside, same era.
A. Juliani, V.-P. Berges, E. Teng, A. Cohen, J. Harper, C. Elion, C. Goy, Y. Gao, H. Henry, M. Mattar et al. , “Unity: A general platform for intelligent agents,” arXiv preprint arXiv:1809.02627 , 2018
Original
2018
Cited alongside, same era.
C. Berner, G. Brockman, B. Chan, V. Cheung, P. Dębiak, C. Dennison, D. Farhi, Q. Fischer, S. Hashme, C. Hesse et al. , “Dota 2 with large scale deep reinforcement learning,” arXiv preprint arXiv:1912.06680 , 2019
Original
2019

Then

C. Ling, K. Tollmar, and L. Gisslén, “Using deep convolutional neural networks to detect rendered glitches in video games,” in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment , vol. 16, no. 1, 2020, pp. 66–73
2020
Later among the works it cites.
J. Bergdahl, C. Gordillo, K. Tollmar, and L. Gisslén, “Augmenting automated game testing with deep reinforcement learning,” in 2020 IEEE Conference on Games (CoG) . IEEE, 2020, pp. 600–603
2020
Later among the works it cites.
S. Risi and J. Togelius, “Increasing generality in machine learning through procedural content generation,” Nature Machine Intelligence , pp. 1–9, 2020
2020
Later among the works it cites.
A. Khalifa, P. Bontrager, S. Earle, and J. Togelius, “Pcgrl: Procedural content generation via reinforcement learning,” arXiv preprint arXiv:2001.09212 , 2020
Original
2020
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

K. Shao, Z. Tang, Y. Zhu, N. Li, and D. Zhao, “A survey of deep reinforcement learning in video games,” arXiv preprint arXiv:1912.10944 , 2019

2019

Cited alongside, same era.

Y. Zheng, X. Xie, T. Su, L. Ma, J. Hao, Z. Meng, Y. Liu, R. Shen, Y. Chen, and C. Fan, “Wuji: Automatic online combat game testing using evolutionary deep reinforcement learning,” in 2019 34th IEEE/ACM International Conference on Automated Software Engineering (ASE) . IEEE, 2019, pp. 772–784

2019

Cited alongside, same era.

R. Wang, J. Lehman, J. Clune, and K. O. Stanley, “Paired open-ended trailblazer (poet): Endlessly generating increasingly complex and diverse learning environments and their solutions,” arXiv preprint arXiv:1901.01753 , 2019

2019

Cited alongside, same era.

P. Bontrager and J. Togelius, “Fully differentiable procedural content generation through generative playing networks,” arXiv preprint arXiv:2002.05259 , 2020

2020

Later among the works it cites.

R. Portelas, C. Colas, K. Hofmann, and P.-Y. Oudeyer, “Teacher algorithms for curriculum learning of deep rl in continuously parameterized environments,” in Conference on Robot Learning . PMLR, 2020, pp. 835–853

2020

Later among the works it cites.