Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning

By Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Anthony Valenzano, Sheila A. McIlraith. International Conference on Machine Learning, 2018

359 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/00ec8123dd2ba03afab7c1fa02f774062f769181

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Sergey Levine
2. Yoshua Bengio
3. William Fedus
4. Pieter Abbeel
5. J. Urgen Schmidhuber
6. Ruslan Salakhutdinov
7. Trevor Darrell
8. Quoc V. Le

Citations in the corpus

• Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning (2020, methodology): “The main contributions of our ICML paper were to introduce RMs and QRM (Toro Icarte et al., 2018c).”
• Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction (2019, background): “The use of additional context variables has by now been demonstrated in a number of settings (Rakelly et al. (2019); Icarte et al. (2018); Ghosh et al. (2018)).”
• Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks (2020, methodology): “For example, Icarte et al. proposed using LTL formulas (Toro Icarte et al. 2018b) and later reward machines (Toro Icarte et al. 2018a) to specify reward functions directly.”