Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A 
ORCID: 0000-0003-4372-5055 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2022)
Difference rewards policy gradients.
.
Abstract
<jats:title>Abstract</jats:title><jats:p>Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing an agent’s contribution to the overall performance, which is crucial for learning good policies. We propose a novel algorithm called Dr.Reinforce that explicitly tackles this by combining difference rewards with policy gradients to allow for learning decentralized policies when the reward function is known. By differencing the reward function directly, Dr.Reinforce avoids difficulties associated with learning the <jats:italic>Q</jats:italic>-function as done by counterfactual multi-agent policy gradients (COMA), a state-of-the-art difference rewards method. For applications where the reward function is unknown, we show the effectiveness of a version of Dr.Reinforce that learns an additional reward network that is used to estimate the difference rewards.</jats:p>
| Item Type: | Conference or Workshop Item (Unspecified) |
|---|---|
| Uncontrolled Keywords: | Multi-agent reinforcement learning, Policy gradients, Difference rewards, Multi-agent credit assignment, Reward learning |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 14 Nov 2022 10:29 |
| Last Modified: | 18 Jan 2023 19:43 |
| DOI: | 10.1007/s00521-022-07960-5 |
| Open Access URL: | https://link.springer.com/article/10.1007/s00521-0... |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3166188 |
Dimensions
Dimensions
