A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments
This addresses a bottleneck in interactive reinforcement learning for robotics, offering an incremental improvement over existing methods.
The paper tackles the problem of limited and single-use advice in Deep Interactive Reinforcement Learning by proposing Broad-persistent Advising (BPA), which retains and reuses advice to improve agent performance in robotic tasks, showing improvements while keeping interaction numbers comparable to baseline methods.
Deep Reinforcement Learning (DeepRL) methods have been widely used in robotics to learn about the environment and acquire behaviors autonomously. Deep Interactive Reinforcement Learning (DeepIRL) includes interactive feedback from an external trainer or expert giving advice to help learners choosing actions to speed up the learning process. However, current research has been limited to interactions that offer actionable advice to only the current state of the agent. Additionally, the information is discarded by the agent after a single use that causes a duplicate process at the same state for a revisit. In this paper, we present Broad-persistent Advising (BPA), a broad-persistent advising approach that retains and reuses the processed information. It not only helps trainers to give more general advice relevant to similar states instead of only the current state but also allows the agent to speed up the learning process. We test the proposed approach in two continuous robotic scenarios, namely, a cart pole balancing task and a simulated robot navigation task. The obtained results show that the performance of the agent using BPA improves while keeping the number of interactions required for the trainer in comparison to the DeepIRL approach.