Abstract
The observable states play a significant role in Reinforcement Learning (RL), meanwhile, the performance of RL is strongly associated with the quality of inferred hidden states. It is a challenging task to accurately extract hidden states because they are often related to both environment’s and agent’s histories, and require numerous domain knowledge. In this work, we aim to leverage history information to improve the performance of agent. Firstly, we discuss that the neglect and usual process of history information are harmful to agent’s performance. Secondly, we propose a novel model that combines the advantage of both supervised learning and RL. Specifically, we extend the framework of classical policy gradient and propose to extract history information using recurrent neural networks. Thirdly, we evaluate our model in simulated physical control environments, outperforming the state-of-the-art models and performing obviously better on more challenging tasks. Finally, we analyze the reasons and suggest possible approaches to extend and scale up the model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Code available at https://github.com/cheunglei/drd.
References
Bengio, Y., Boulanger-Lewandowski, N., Pascanu, R.: Advances in optimizing recurrent networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 8624–8628 (2013)
Brockman, G., et al.: OpenAI gym (2016). http://arxiv.org/abs/1606.01540
Dhariwal, P., et al.: OpenAI baselines (2017). https://github.com/openai/baselines
Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control. In: International Conference on Machine Learning, pp. 1329–1338 (2016)
François-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J., et al.: An introduction to deep reinforcement learning. Found. Trends Mach. Learn. 11(3–4), 219–354 (2018)
Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: International Conference on Machine Learning, pp. 1582–1591 (2018)
Garnier, P., Viquerat, J., Rabault, J., Larcher, A., Kuhnle, A., Hachem, E.: A review on deep reinforcement learning for fluid mechanics (2019). http://arxiv.org/abs/1908.04127
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International Conference on Machine Learning, pp. 1856–1865 (2018)
van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: AAAI Conference on Artificial Intelligence, pp. 2094–2100 (2016)
Hausknecht, M.J., Stone, P.: Deep recurrent Q-learning for partially observable MDPs. In: 2015 AAAI Fall Symposia, pp. 29–37 (2015). http://www.aaai.org/ocs/index.php/FSS/FSS15/paper/view/11673
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Kapturowski, S., Ostrovski, G., Quan, J., Munos, R., Dabney, W.: Recurrent experience replay in distributed reinforcement learning. In: International Conference on Learning Representations (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)
Li, X., et al.: Recurrent reinforcement learning: a hybrid approach (2015). http://arxiv.org/abs/1509.03044
Li, Y., Zheng, W., Zheng, Z.: Deep robust reinforcement learning for practical algorithmic trading. IEEE Access 7, 108014–108022 (2019)
Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. In: International Conference on Learning Representations (2016)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928–1937 (2016)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889–1897 (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017). http://arxiv.org/abs/1707.06347
Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387–395 (2014)
Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 5026–5033 (2012)
Wang, J.X., et al.: Learning to reinforcement learn (2016). http://arxiv.org/abs/1611.05763
Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995–2003 (2016)
Wu, Y., Mansimov, E., Grosse, R.B., Liao, S., Ba, J.: Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation. In: Advances in Neural Information Processing Systems, pp. 5279–5288 (2017)
Acknowledgments
This work was supported by the National Natural Science Foundation of China under Grant Nos. 61300049, 61763003; the National Key R&D Program of China under Grant No. 2017YFB1003103; and the Natural Science Research Foundation of Jilin Province of China under Grant Nos. 20180101053JC, 20190201193JC.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, L., Han, S., Zhang, Z., Li, L., Lü, S. (2020). Deep Recurrent Deterministic Policy Gradient for Physical Control. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_21
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)