Building action sets in a deep reinforcement learner
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 app...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2021
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/sis_research/6785 https://ink.library.smu.edu.sg/context/sis_research/article/7788/viewcontent/ICMLA_21_final_1_.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | 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. |
|---|