loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Doğay Kamar 1 ; Nazím Kemal Üre 2 ; 1 and Gözde Ünal 2 ; 1

Affiliations: 1 Faculty of Computer and Informatics, Istanbul Technical University, Istanbul, Turkey ; 2 Artificial Intelligence and Data Science Research Center, Istanbul Technical University, Istanbul, Turkey

Keyword(s): Deep Learning, Reinforcement Learning, Generative Adversarial Networks, Efficient Exploration in Reinforcement Learning.

Abstract: In this study, we address the problem of efficient exploration in reinforcement learning. Most common exploration approaches depend on random action selection, however these approaches do not work well in environments with sparse or no rewards. We propose Generative Adversarial Network-based Intrinsic Reward Module that learns the distribution of the observed states and sends an intrinsic reward that is computed as high for states that are out of distribution, in order to lead agent to unexplored states. We evaluate our approach in Super Mario Bros for a no reward setting and in Montezuma’s Revenge for a sparse reward setting and show that our approach is indeed capable of exploring efficiently. We discuss a few weaknesses and conclude by discussing future works.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 54.210.126.232

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kamar, D.; Üre, N. and Ünal, G. (2022). GAN-based Intrinsic Exploration for Sample Efficient Reinforcement Learning. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-547-0; ISSN 2184-433X, SciTePress, pages 264-272. DOI: 10.5220/0010825500003116

@conference{icaart22,
author={Doğay Kamar. and Nazím Kemal Üre. and Gözde Ünal.},
title={GAN-based Intrinsic Exploration for Sample Efficient Reinforcement Learning},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2022},
pages={264-272},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010825500003116},
isbn={978-989-758-547-0},
issn={2184-433X},
}

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - GAN-based Intrinsic Exploration for Sample Efficient Reinforcement Learning
SN - 978-989-758-547-0
IS - 2184-433X
AU - Kamar, D.
AU - Üre, N.
AU - Ünal, G.
PY - 2022
SP - 264
EP - 272
DO - 10.5220/0010825500003116
PB - SciTePress