Ego Networks
Pages 488 - 499
Abstract
Games on the Atari 2600 platform have served as a benchmark for reinforcement learning algorithms in recent years, and while deep reinforcement learning approaches make progress on most games, there are still some games that the majority of these algorithms struggle with. These are called hard exploration games. We introduce two new developments for the Random Network Distillation (RND) architecture. We apply self-attention and the mechanism of ego motion on the RND architecture and we evaluate them on three hard exploration tasks from the Atari platform. We find that the proposed ego network model improve the baseline of the RND architecture on these tasks.
References
[1]
Aytar, Y., Pfaff, T., Budden, D., Paine, T., Wang, Z., de Freitas, N.: Playing hard exploration games by watching YouTube. In: NeurIPS (2018)
[2]
Badia, A.P., et al.: Agent57: outperforming the Atari human benchmark. ArXiv abs/2003.13350 (2020)
[3]
Badia, A.P., et al.: Never give up: learning directed exploration strategies. ArXiv abs/2002.06038 (2020)
[4]
Bellemare MG, Naddaf Y, Veness J, and Bowling M The arcade learning environment: an evaluation platform for general agents (extended abstract) J. Artif. Intell. Res. 2013 47 253-279
[5]
Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. ArXiv abs/1606.01868 (2016)
[6]
Bello, I., Zoph, B., Vaswani, A., Shlens, J., Le, Q.V.: Attention Augmented Convolutional Networks. arXiv e-prints arXiv:1904.09925, April 2019
[7]
Burda, Y., Edwards, H., Storkey, A.J., Klimov, O.: Exploration by random network distillation. CoRR abs/1810.12894 (2018). http://arxiv.org/abs/1810.12894
[8]
Burda, Y., Edwards, H.A., Pathak, D., Storkey, A.J., Darrell, T., Efros, A.A.: Large-scale study of curiosity-driven learning. ArXiv abs/1808.04355 (2019)
[9]
Choi, J., Lee, B., Zhang, B.: Multi-focus attention network for efficient deep reinforcement learning. ArXiv abs/1712.04603 (2017)
[10]
Choi, J., et al.: Contingency-aware exploration in reinforcement learning. ArXiv abs/1811.01483 (2019)
[11]
Haber, N., Mrowca, D., Fei-Fei, L., Yamins, D.L.K.: Emergence of structured behaviors from curiosity-based intrinsic motivation. CoRR abs/1802.07461 (2018). http://arxiv.org/abs/1802.07461
[12]
Horgan, D., et al.: Distributed prioritized experience replay. ArXiv abs/1803.00933 (2018)
[13]
Kapturowski, S., Ostrovski, G., Dabney, W., Quan, J., Munos, R.: Recurrent experience replay in distributed reinforcement learning. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=r1lyTjAqYX
[14]
Martin, J., Sasikumar, S.N., Everitt, T., Hutter, M.: Count-based exploration in feature space for reinforcement learning. In: IJCAI (2017)
[15]
Mott, A., Zoran, D., Chrzanowski, M., Wierstra, D., Rezende, D.J.: Towards interpretable reinforcement learning using attention augmented agents. In: NeurIPS (2019)
[16]
Ostrovski, G., Bellemare, M.G., Oord, A., Munos, R.: Count-based exploration with neural density models. ArXiv abs/1703.01310 (2017)
[17]
Ostrovski, G., Bellemare, M.G., van den Oord, A., Munos, R.: Count-based exploration with neural density models. ArXiv abs/1703.01310 (2017)
[18]
Schrittwieser, J., et al.: Mastering Atari, go, chess and shogi by planning with a learned model. ArXiv abs/1911.08265 (2019)
[19]
Sorokin, I., Seleznev, A., Pavlov, M., Fedorov, A., Ignateva, A.: Deep attention recurrent Q-network. ArXiv abs/1512.01693 (2015)
[20]
Tang, H., et al.: Exploration: a study of count-based exploration for deep reinforcement learning. In: NIPS (2017)
[21]
Tang, Y., Nguyen, D., Ha, D.: Neuroevolution of self-interpretable agents. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference (2020)
Recommendations
Ego-net digger: a new way to study ego networks in online social networks
HotSocial '12: Proceedings of the First ACM International Workshop on Hot Topics on Interdisciplinary Social Networks ResearchThe vast proliferation of Online Social Networks (OSN) is generating many new ways to interact and create social relationships with others. While substantial results have been obtained in anthropology literature describing the properties of human social ...
Ego network structure in online social networks and its impact on information diffusion
In the last few years, Online Social Networks (OSNs) attracted the interest of a large number of researchers, thanks to their central role in the society. Through the analysis of OSNs, many social phenomena have been studied, such as the viral diffusion ...
Ego network models for Future Internet social networking environments
In this paper we present constructive algorithms for generating realistic synthetic ego networks (one of the most important representations of human social networks). These algorithms are based on ego network models derived in the anthropology ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Dec 2021
718 pages
ISBN:978-3-030-92184-2
DOI:10.1007/978-3-030-92185-9
© Springer Nature Switzerland AG 2021.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 08 December 2021
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Jan 2025