Abstract
Reward shaping has been proposed as a means to address the credit assignment problem in Multi-Agent Systems (MAS). Two popular shaping methods are Potential-Based Reward Shaping and difference rewards, and both have been shown to improve learning speed and the quality of joint policies learned by agents in single-objective MAS. In this work we discuss the theoretical implications of applying these approaches to multi-objective MAS, and evaluate their efficacy using a new multi-objective benchmark domain where the true set of Pareto optimal system utilities is known.
| Original language | English (Ireland) |
|---|---|
| Title of host publication | A Theoretical and Empirical Analysis of Reward Transformations in Multi-Objective Stochastic Games |
| Number of pages | 3 |
| Publication status | Published - 1 Jan 2017 |
Authors (Note for portal: view the doc link for the full list of authors)
- Authors
- Mannion, P,Duggan, J,Howley, E,
Fingerprint
Dive into the research topics of 'AAMAS17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver