Symmetry Learning for Function Approximation in Reinforcement Learning
By Anuj Mahajan, Theja Tulabandhula. 2017
32 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Cognitive Neuroscience
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Shimon Whiteson
- Tabish Rashid
- Anuj Mahajan
- Mikayel Samvelyan
- Tim G. J. Rudner
- Matthew R. Fellows
- Chongjie Zhang
- Tonghan Wang
In Cognitive Neuroscience
Citations in the corpus
- MAVEN: Multi-Agent Variational Exploration (2019, background): “RL[33] (by increasing sample inefficiency[31, 30]), but also by interacting with the representational constraints necessary for decentralisation to push the algorithm towards suboptimal policies.”
- VIREL: A Variational Inference Framework for Reinforcement Learning (2018, methodology): “As immediate future work, our focus is to find better estimates of εω to provide a principled method for uncertainty based exploration; we expect it to help attain sample efficiency in conjunction with various methods like [39, 40].”