Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
OPEN ACCESS
Loading...
Author / Producer
Date
2022-07
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
We consider model-based multi-agent reinforcement learning, where the environment transition model is unknown and can only be learned via expensive interactions with the environment. We propose H-MARL (Hallucinated Multi-Agent Reinforcement Learning), a novel sample-efficient algorithm that can efficiently balance exploration, i.e., learning about the environment, and exploitation, i.e., achieve good equilibrium performance in the underlying general-sum Markov game. H-MARL builds high-probability confidence intervals around the unknown transition model and sequentially updates them based on newly observed data. Using these, it constructs an optimistic hallucinated game for the agents for which equilibrium policies are computed at each round. We consider general statistical models (e.g., Gaussian processes, deep ensembles, etc.) and policy classes (e.g., deep neural networks), and theoretically analyze our approach by bounding the agents’ dynamic regret. Moreover, we provide a convergence rate to the equilibria of the underlying Markov game. We demonstrate our approach experimentally on an autonomous driving simulation benchmark. H-MARL learns successful equilibrium policies after a few interactions with the environment and can significantly improve the performance compared to non-optimistic exploration methods.
Permanent link
Publication status
published
Book title
Proceedings of the 39th International Conference on Machine Learning
Journal / series
Volume
162
Pages / Article No.
19580 - 19597
Publisher
PMLR
Event
39th International Conference on Machine Learning (ICML 2022)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
09578 - Kamgarpour, Maryam (ehemalig) / Kamgarpour, Maryam (former)
03908 - Krause, Andreas / Krause, Andreas
Notes
Funding
180545 - NCCR Automation (phase I) (SNF)
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)