Improving interactive reinforcement learning: What makes a good teacher?

Abstract

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which uses a parent-like trainer to propose the next action to be performed and by doing so reduces the search space by advice. On some occasions, the trainer may be another artificial agent which in turn was trained using reinforcement learning methods to afterward becoming an advisor for other learner-agents. In this work, we analyze internal representations and characteristics of artificial agents to determine which agent may outperform others to become a better trainer-agent. Using a polymath agent, as compared to a specialist agent, an advisor leads to a larger reward and faster convergence of the reward signal and also to a more stable behavior in terms of the state visit frequency of the learner-agents. Moreover, we analyze system interaction parameters in order to determine how influential they are in the apprenticeship process, where the consistency of feedback is much more relevant when dealing with different learner obedience parameters.

21 pages, 12 figures

Cited by in corpus (10)

• Survey on reinforcement learning for language processing
• Deep Reinforcement Learning with Interactive Feedback in a Human-Robot Environment
• Explainable robotic systems: Understanding goal-driven actions in a reinforcement learning scenario
• Human Engagement Providing Evaluative and Informative Advice for Interactive Reinforcement Learning
• A Conceptual Framework for Externally-influenced Agents: An Assisted Reinforcement Learning Review
• AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learning
• Interactive Reinforcement Learning for Feature Selection with Decision Tree in the Loop
• Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
• A Broad-persistent Advising Approach for Deep Interactive Reinforcement Learning in Robotic Environments
• Reward Shaping with Dynamic Trajectory Aggregation