Abstract
Sparse-reward reinforcement learning environments pose a particular challenge because the agent receives infrequent rewards, making it difficult to learn an optimal policy. In this paper, we propose NSSE, a novel approach that combines that stratified state space exploration with prioritised sweeping to enhance the informativeness of learning, thus enabling fast learning convergence. We evaluate NSSE on three typical Atari sparse reward environments. The results demonstrate that our state space exploration method exhibits strong performance compared to two baseline algorithms: Deep Q-Network (DQN) and noisy Deep Q-Network (Noisy DQN).
Dr Yang is supported by Royal Academy Engineering SHE project RAEng (IF2223-172) and Royal Society of Edinburgh (961_Yang).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aubret, A., Matignon, L., Hassas, S.: An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey. Entropy 25(2), 327 (2023)
Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253–279 (2013)
Bellman, R.: A Markovian decision process. J. Math. Mech. 679–684 (1957)
Burda, Y., Edwards, H., Storkey, A., Klimov, O.: Exploration by random network distillation. arXiv preprint arXiv:1810.12894 (2018)
Ecoffet, A., Huizinga, J., Lehman, J., Stanley, K.O., Clune, J.: First return, then explore. Nature 590(7847), 580–586 (2021)
Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)
Hester, T., et al.: Deep Q-learning from demonstrations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)
Horgan, D., et al.: Distributed prioritized experience replay. arXiv preprint arXiv:1803.00933 (2018)
Jo, D., et al.: LECO: learnable episodic count for task-specific intrinsic reward. Adv. Neural. Inf. Process. Syst. 35, 30432–30445 (2022)
Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: International Conference on Machine Learning, pp. 2778–2787. PMLR (2017)
Puterman, M.L.: Markov decision processes: discrete stochastic dynamic programming. In: Wiley Series in Probability and Statistics (1994)
Saglam, B., Mutlu, F.B., Cicek, D.C., Kozat, S.S.: Actor prioritized experience replay. arXiv preprint arXiv:2209.00532 (2022)
Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)
Seo, Y., Chen, L., Shin, J., Lee, H., Abbeel, P., Lee, K.: State entropy maximization with random encoders for efficient exploration. In: International Conference on Machine Learning, pp. 9443–9454. PMLR (2021)
Yu, X., Lyu, Y., Tsang, I.: Intrinsic reward driven imitation learning via generative model. In: International Conference on Machine Learning, pp. 10925–10935. PMLR (2020)
Yuan, M., Pun, M.O., Wang, D.: Rényi state entropy maximization for exploration acceleration in reinforcement learning. IEEE Trans. Artif. Intell. (2022)
Zheng, C., Yang, S., Parra-Ullauri, J.M., Garcia-Dominguez, A., Bencomo, N.: Reward-reinforced generative adversarial networks for multi-agent systems. IEEE Trans. Emerg. Top. Comput. Intell. 6, 479–488 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liu, X. et al. (2023). A Novel State Space Exploration Method for the Sparse-Reward Reinforcement Learning Environment. In: Bramer, M., Stahl, F. (eds) Artificial Intelligence XL. SGAI 2023. Lecture Notes in Computer Science(), vol 14381. Springer, Cham. https://doi.org/10.1007/978-3-031-47994-6_18
Download citation
DOI: https://doi.org/10.1007/978-3-031-47994-6_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47993-9
Online ISBN: 978-3-031-47994-6
eBook Packages: Computer ScienceComputer Science (R0)