Broad-persistent Advice for Interactive Reinforcement Learning Scenarios
This addresses the inefficiency of advice retention in interactive reinforcement learning, offering a domain-specific improvement for autonomous agent training.
The paper tackled the problem of interactive reinforcement learning agents discarding user advice after single use by introducing a method to retain and reuse broad advice, resulting in improved agent performance and reduced trainer interactions.
The use of interactive advice in reinforcement learning scenarios allows for speeding up the learning process for autonomous agents. Current interactive reinforcement learning research has been limited to real-time interactions that offer relevant user advice to the current state only. Moreover, the information provided by each interaction is not retained and instead discarded by the agent after a single use. In this paper, we present a method for retaining and reusing provided knowledge, allowing trainers to give general advice relevant to more than just the current state. Results obtained show that the use of broad-persistent advice substantially improves the performance of the agent while reducing the number of interactions required for the trainer.