Castellini, Jacopo, Devlin, Sam, Oliehoek, Frans A 
ORCID: 0000-0003-4372-5055 and Savani, Rahul ORCID: 0000-0003-1262-7831
(2020)
Difference Rewards Policy Gradients.
[Internet Publication]
|
Text
2012.11258v1.pdf - Published version Download (1MB) | Preview |
Abstract
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 Q-function as done by Counterfactual Multiagent 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.
| Item Type: | Internet Publication |
|---|---|
| Additional Information: | This work as been accepted as an Extended Abstract in Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), U. Endriss, A. Now\'e, F. Dignum, A. Lomuscio (eds.), May 3-7 2021, Online |
| Uncontrolled Keywords: | cs.MA, cs.MA, cs.LG, I.2.6; I.2.11 |
| Depositing User: | Symplectic Admin |
| Date Deposited: | 12 Jan 2021 11:44 |
| Last Modified: | 21 Nov 2023 12:51 |
| Related URLs: | |
| URI: | https://livrepository.liverpool.ac.uk/id/eprint/3111305 |
Share
Share
