Advice taking in multiagent reinforcement learning

This paper proposes the β-WoLF algorithm for multiagent reinforcement learning (MARL) in the stochastic games framework that uses an additional “advice” signal to inform agents about mutually beneficial forms of behaviour. β-WoLF is an extension of the WoLF-PHC algorithm that allows agents to assess whether the advice obtained through this additional reward signal is (i) useful for the learning agent itself and (ii) currently being followed by other agents in the system. With this, agents are able to decide autonomously whether to follow the advice or not, safeguarding themselves against malicious or unreliable advice which, if followed, might lead them to sacrifice their own future rewards, as well as unilateral cooperation that could be exploited by other agents in the system. We report on experimental results obtained with this novel algorithm which indicate that it enables cooperation in scenarios in which the need to defend oneself against exploitation results in poor coo...

• Type: Conference
• Year: 2007
• Where: ATAL
• Authors: Michael Rovatsos, Alexandros Belesiotis
• Keywords: ATAL 2007, MARL Algorithms, Multiagent Reinforcement, Reinforcement Learning