Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
12-2021
Abstract
In many policy-learning applications, the agent may execute a set of actions at each decision stage. Choosing among an exponential number of alternatives poses a computational challenge, and even representing actions naturally expressed as sets can be a tricky design problem. Building upon prior approaches that employ deep neural networks and iterative construction of action sets, we introduce a reward-shaping approach to apportion reward to each atomic action based on its marginal contribution within an action set, thereby providing useful feedback for learning to build these sets. We demonstrate our method in two environments where action spaces are combinatorial. Experiments reveal that our method significantly accelerates and stabilizes policy learning with combinatorial actions.
Discipline
Artificial Intelligence and Robotics | Software Engineering
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 20th IEEE International Conference on Machine Learning and Applications, Virtual Conference, 2021 December 13-15
First Page
484
Last Page
489
ISBN
9781665443371
Identifier
10.1109/ICMLA52953.2021.00081
City or Country
Virtual Conference
Citation
WANG, Yongzhao; SINHA, Arunesh; WANG, Sky C.H.; and WELLMAN, Michael P..
Building action sets in a deep reinforcement learner. (2021). Proceedings of the 20th IEEE International Conference on Machine Learning and Applications, Virtual Conference, 2021 December 13-15. 484-489.
Available at: https://ink.library.smu.edu.sg/sis_research/6785
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.