- TL;DR: A new RL algorithm called Interior Policy Differentiation is proposed to learn a collection of diverse policies for a given primal task.
- Abstract: Animals develop novel skills not only through the interaction with the environment but also from the influence of the others. In this work we model the social influence into the scheme of reinforcement learning, enabling the agents to learn both from the environment and from their peers. Specifically, we first define a metric to measure the distance between policies then quantitatively derive the definition of uniqueness. Unlike previous precarious joint optimization approaches, the social uniqueness motivation in our work is imposed as a constraint to encourage the agent to learn a policy different from the existing agents while still solve the primal task. The resulting algorithm, namely Interior Policy Differentiation (IPD), brings about performance improvement as well as a collection of policies that solve a given task with distinct behaviors
- Keywords: Reinforcement Learning, Social Uniqueness, Policy Differentiation
- Original Pdf: pdf