Simultaneously Learning and Advising in Multiagent Reinforcement Learning

摘要

Reinforcement Learning has long been employed to solve sequential decision-making problems with minimal input data. However, the classical approach requires a large number of interactions with an environment to learn a suitable policy. This problem is further intensified when multiple autonomous agents are simultaneously learning in the same environment. The teacher-student approach aims at alleviating this problem by integrating an advising procedure in the learning process, in which an experienced agent (human or not) can advise a student to guide her exploration. Even though previous works reported that an agent can learn faster when receiving advice, their proposals require that the teacher is an expert in the learning task. Sharing successful episodes can also accelerate learning, but this procedure requires a lot of communication between agents, which is unfeasible for domains in which communication is limited. Thus, we here propose a multiagent advising framework where multiple agents can advise each other while learning in a shared environment. If in any state an agent is unsure about what to do, it can ask for advice to other agents and may receive answers from agents that have more confidence in their actuation for that state. We perform experiments in a simulated Robot Soccer environment and show that the learning process is improved by incorporating this kind of advice.