Theoretically-Grounded Policy Advice from Multiple Teachers in Reinforcement Learning Settings with Applications to Negative Transfer

Abstract

Policy advice is a transfer learning method where a student agent is able to learn faster via advice from a teacher. However, both this and other reinforcement learning transfer methods have little theoretical analysis. This paper formally defines a setting where multiple teacher agents can provide advice to a student and introduces an algorithm to leverage both autonomous exploration and teacher's advice. Our regret bounds justify the intuition that good teachers help while bad teachers hurt. Using our formalization, we are also able to quantify, for the first time, when negative transfer can occur within such a reinforcement learning setting.

arXiv comment10 pages, 6 figures, IJCAI 2016 conference paper

Cited by in corpus (6)

• Using Reinforcement Learning in the Algorithmic Trading Problem
• Agent-Agnostic Human-in-the-Loop Reinforcement Learning
• AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
• Student-Initiated Action Advising via Advice Novelty
• Parallel Knowledge Transfer in Multi-Agent Reinforcement Learning
• Learning Deterministic Policy with Target for Power Control in Wireless Networks