In this paper we explore methods to exploit symmetries for ensuring sample efficiency in reinforcement learning (RL), this problem deserves ever increasing attention with the recent advances in the use of deep networks for complex RL tasks which require large amount of training data. We introduce a novel method to detect symmetries using reward trails observed during episodic experience and prove its completeness. We also provide a framework to incorporate the discovered symmetries for functional approximation. Finally we show that the use of potential based reward shaping is especially effective for our symmetry exploitation mechanism. Experiments on various classical problems show that our method improves the learning performance significantly by utilizing symmetry information.
- Pub Date:
- June 2017
- Statistics - Machine Learning;
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning
- 12 pages, 3 figures. A preliminary version appears in AAMAS 2017. Also presented at the 3rd Multidisciplinary Conference on Reinforcement Learning and Decision Making