Some Supervision Required: Incorporating Oracle Policies in Reinforcement Learning via Epistemic Uncertainty Metrics

no code implementations • 22 Aug 2022 • Jun Jet Tai, Jordan K. Terry, Mauro S. Innocente, James Brusey, Nadjim Horri

In the case of using an oracle policy, it can be unclear how best to incorporate the oracle policy's experience into the learning policy in a way that maximizes learning sample efficiency.

reinforcement-learning Reinforcement Learning (RL)