Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning
This addresses a specific bottleneck in RLfD for AI agents, but it is incremental as it builds on existing RLfD methods.
The paper tackles the problem of ambiguous demonstrations in reinforcement learning from demonstrations (RLfD), which can hinder training stability and efficiency, by proposing the SERLfD framework that uses self-explanation to interpret successful trajectories, resulting in improved training stability and performance for RLfD models.
Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the RL-Agent from learning stably and efficiently. Since an optimal demonstration may also suffer from being ambiguous, previous works that combine RL and learning from demonstration (RLfD works) may not work well. Inspired by how humans handle such situations, we propose to use self-explanation (an agent generates explanations for itself) to recognize valuable high-level relational features as an interpretation of why a successful trajectory is successful. This way, the agent can provide some guidance for its RL learning. Our main contribution is to propose the Self-Explanation for RL from Demonstrations (SERLfD) framework, which can overcome the limitations of traditional RLfD works. Our experimental results show that an RLfD model can be improved by using our SERLfD framework in terms of training stability and performance.