Abstract
Proximal and trust-region policy optimization methods (PPO and TRPO) belong to the standard reinforcement learning toolbox. Notably, PPO can be viewed as transforming the constrained TRPO problem into an unconstrained one, either via turning the constraint into a penalty or via objective clipping. In this chapter, an alternative problem reformulation is studied, where the information loss is bounded using a novel transformation of the KullbackLeibler (KL) divergence constraint. In contrast to PPO, the considered method does not require tuning of the regularization parameter, which is known to be hard due to its sensitivity to the reward scaling. The resulting algorithm, termed information-loss-bounded policy optimization (ILBPO), both enjoys the benefits of the first-order methods, being straightforward to implement using automatic differentiation, and maintains the advantages of the quasi-second order methods. It performs competitively in simulated OpenAI MuJoCo environments and achieves robust performance on a real robotic task of the Furuta pendulum swing-up and stabilization.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amari, S.I.: Natural gradient works efficiently in learning. Neural Comput. 10(2), 251–276 (1998)
Bagnell, J.A., Schneider, J.: Covariant policy search. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI), pp. 1019–1024. Morgan Kaufmann Publishers Inc. (2003)
Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., Tang, J., Zaremba, W.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)
Dhariwal, P., Hesse, C., Klimov, O., Nichol, A., Plappert, M., Radford, A., Schulman, J., Sidor, S., Wu, Y., Zhokhov, P.: Openai Baselines (2017)
Fantoni, I., Lozano, R.: Non-linear Control for Underactuated Mechanical Systems. Springer Science & Business Media (2001)
Kakade, S.M.: A natural policy gradient. In: Advances in Neural Information Processing Systems (NIPS), pp. 1531–1538 (2002)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Minsky, M.: Steps toward artificial intelligence. Proc. IRE 49(1), 8–30 (1961)
Peters, J., Mülling, K., Altun, Y.: Relative entropy policy search. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence (AAAI), pp. 1607–1612 (2010)
Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning (ICML), pp. 1889–1897 (2015)
Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. arXiv preprint arXiv:1506.02438 (2015)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)
Sutton, R.S., McAllester, D.A., Singh, S.P., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems (NIPS), pp. 1057–1063 (2000)
Todorov, E., Erez, T., Tassa, Y.: Mujoco: A physics engine for model-based control. In: International Conference on Intelligent Robots and Systems (IROS), pp. 5026–5033 (2012)
Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3–4), 229–256 (1992)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Song, Y. (2021). Information-Loss-Bounded Policy Optimization. In: Belousov, B., Abdulsamad, H., Klink, P., Parisi, S., Peters, J. (eds) Reinforcement Learning Algorithms: Analysis and Applications. Studies in Computational Intelligence, vol 883. Springer, Cham. https://doi.org/10.1007/978-3-030-41188-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-41188-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-41187-9
Online ISBN: 978-3-030-41188-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)