Interactive Reinforcement Learning with Dynamic Reuse of Prior Knowledge from Human and Agent Demonstrations

Reinforcement learning has enjoyed multiple impressive successes in recent years. However, these successes typically require very large amounts of data before an agent achieves acceptable performance. This paper focuses on a novel way of combating such requirements by leveraging existing (human or agent) knowledge. In particular, this paper leverages demonstrations, allowing an agent to quickly achieve high performance. This paper introduces the Dynamic Reuse of Prior (DRoP) algorithm, which combines the offline knowledge (demonstrations recorded before learning) with an online confidence-based performance analysis. DRoP leverages the demonstrator’s knowledge by automatically balancing between reusing the prior knowledge and the current learned policy, allowing the agent to outperform the original demonstrations. We compare with multiple state-of-theart learning algorithms and empirically show that DRoP can achieve superior performance in two domains. Additionally, we show that this confidence measure can be used to selectively request additional demonstrations, significantly improving the learning performance of the agent.