Flexibility of Emulation Learning from Pioneers in Nonstationary Environments

Abstract

In imitation learning, the agent observes specific action-state pair sequences of another agent (expert) and somehow reflect them into its own action. One of its implementations in reinforcement learning is the inverse reinforcement learning. We propose a new framework for social learning, emulation learning, which requires much less information from another agent (pioneer). In emulation learning, the agent is given only a certain level of achievement (accumulated rewards per episode). In this study, we implement emulation learning in the reinforcement learning setting by applying a model of satisficing action policy. We show that the emulation learning algorithm works well in a non-stationary reinforcement learning tasks, breaking the often observed trade-off like relationship between optimality and flexibility.