30 citations · 115 across the 26 of their papers we have counts for
6 papers · 1 filter
Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction
Taher Jafferjee, Juliusz Ziomek, Tianpei Yang +6
Centralised training with decentralised execution (CT-DE) serves as the foundation of many leading multi-agent reinforcement learning (MARL) algorithms. Despite its popularity, it…
SEREN: Knowing When to Explore and When to Exploit
Changmin Yu, David Mguni, Dong Li +3
Efficient reinforcement learning (RL) involves a trade-off between "exploitative" actions that maximise expected reward and "explorative'" ones that sample unvisited states. To enc…
On the Convergence of Fictitious Play: A Decomposition Approach
Yurong Chen, Xiaotie Deng, Chenchen Li +4
Fictitious play (FP) is one of the most fundamental game-theoretical learning frameworks for computing Nash equilibrium in -player games, which builds the foundation for modern…
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
David Mguni, Aivar Sootla, Juliusz Ziomek +4
Many real-world settings involve costs for performing actions; transaction costs in financial systems and fuel costs being common examples. In these settings, performing actions at…
A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
Oliver Slumbers, David Henry Mguni, Stephen Marcus McAleer +3
In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other agents. However, the dominant paradigm in game t…
Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentation
Aivar Sootla, Alexander I. Cowen-Rivers, Taher Jafferjee +4
Satisfying safety constraints almost surely (or with probability one) can be critical for the deployment of Reinforcement Learning (RL) in real-life applications. For example, plan…