Lenient Multi-Agent Deep Reinforcement Learning

Palmer, Gregory, Tuyls, Karl, Bloembergen, Daan and Savani, Rahul ORCID: 0000-0003-1262-7831 (2018) Lenient Multi-Agent Deep Reinforcement Learning .

Text 1707.04402v1.pdf - Submitted version Download (479kB)

Abstract

Much of the success of single agent deep reinforcement learning (DRL) in recent years can be attributed to the use of experience replay memories (ERM), which allow Deep Q-Networks (DQNs) to be trained efficiently through sampling stored state transitions. However, care is required when using ERMs for multi-agent deep reinforcement learning (MA-DRL), as stored transitions can bec ome outdated when agents update their policies in parallel (9). In this work we apply leniency (22] to MA-DRL Lenient agents map state-action pairs to decaying temperature values that control the amount of leniency applied towards negative policy updates that are sampled from the ERM. This introduces optimism in the value- function update, and has been shown to facilitate cooperation in tabular fully-cooperative multi-agent reinforcement learning probl ems. We evaluate our Lenient-DQN (LDQN) empirically against the related Hysteretic-DQN (HDQN) algorithm [20) as well as a modi fied version we call scheduled-HDQN, that uses average reward learning near terminal states. Evaluations take place in extended variations of the Coordinated Multi-Agent Object Transportation Problem (CMOTP) [6). We find that LDQN agents are more likely to converge to the optimal policy in a stochastic reward CMOTP compared to standard and scheduled-HDQN agents.

Item Type:	Conference Item (Unspecified)
Additional Information:	9 pages, 6 figures, AAMAS2018 Conference Proceedings
Uncontrolled Keywords:	Multi-Agent Deep Reinforcement Learning, Leniency
Depositing User:	Symplectic Admin
Date Deposited:	16 Oct 2017 10:16
Last Modified:	23 May 2026 01:03
Related Websites:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3009868
Disclaimer:	The University of Liverpool is not responsible for content contained on other websites from links within repository metadata. Please contact us if you notice anything that appears incorrect or inappropriate.