Towards Intrinsic Interactive Reinforcement Learning: A Survey

Reinforcement learning (RL) and brain-computer interfaces (BCI) are two fields that have been growing over the past decade. Until recently, these fields have operated independently of one another. With the rising interest in human-in-the-loop (HITL) applications, RL algorithms have been adapted to account for human guidance giving rise to the sub-field of interactive reinforcement learning (IRL). Adjacently, BCI applications have been long interested in extracting intrinsic feedback from neural activity during human-computer interactions. These two ideas have set RL and BCI on a collision course for one another through the integration of BCI into the IRL framework where intrinsic feedback can be utilized to help train an agent. This intersection has been denoted as intrinsic IRL. To further help facilitate deeper ingratiation of BCI and IRL, we provide a review of intrinsic IRL with an emphasis on its parent field of feedback-driven IRL while also providing discussions concerning the validity, challenges, and future research directions.