Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance
This work addresses the challenge of using imperfect demonstrations in RLfD, which is a common issue in real-world applications, representing an incremental advance over prior methods.
The paper tackles the problem of reinforcement learning from imperfect demonstrations by formalizing the imperfect expert setting and addressing optimality and convergence issues, resulting in a method that achieves consistent improvement over existing RLfD counterparts.
In this paper, we study Reinforcement Learning from Demonstrations (RLfD) that improves the exploration efficiency of Reinforcement Learning (RL) by providing expert demonstrations. Most of existing RLfD methods require demonstrations to be perfect and sufficient, which yet is unrealistic to meet in practice. To work on imperfect demonstrations, we first define an imperfect expert setting for RLfD in a formal way, and then point out that previous methods suffer from two issues in terms of optimality and convergence, respectively. Upon the theoretical findings we have derived, we tackle these two issues by regarding the expert guidance as a soft constraint on regulating the policy exploration of the agent, which eventually leads to a constrained optimization problem. We further demonstrate that such problem is able to be addressed efficiently by performing a local linear search on its dual form. Considerable empirical evaluations on a comprehensive collection of benchmarks indicate our method attains consistent improvement over other RLfD counterparts.