… a teacher–student framework for reinforcement learning, … Agents advising agents in
reinforcement learning. {Proceedings of … {Proceedings of the adaptive and learning agents …

… Recent work has been using reinforcement learning techniques to address this problem (…
Our work combines reinforcement learning and rich language advice, providing an efficient …

… a reinforcement learning problem (Section 4.1), ie, the teacher agent needs to learn a policy
for deciding when to give advice. … the teacher can learn a better policy for giving advice than …

… learning model of action advice under a budget. We focus on reinforcement learning teachers
providing action advice to … advice budget. First, we examine several critical factors affecting …

… throughout learning; while teacher advice is used during learning, … (ie, in absence of teacher
advice actions, such that AUC … Reinforcement learning agents providing advice in complex …

… In this framework, a teacher agent … , the teacher may only give such advice a limited number
of times. We present several novel algorithms that teachers can use to budget their advice …

… Our contributions in this study are as follows: First, we show that it is possible to generalise
teacher advice across similar states in deep RL with high accuracy. Second, we present a RL …

… the learning process for RL. … reinforcement learning (IRL) allows to speed up the apprenticeship
process by using a parent-like advisor to support the learning by delivering useful advice …

… All the aforementioned works rely on a single teacher (that follows a fixed policy) to give
advice, but we are interested in a situation in which multiple potential policies may be used to …

… teacher-advice mechanism with Gaussian process (TAG) by leveraging a few expert
demonstrations. In TAG, a teacher model is built to provide both an advice … , the teacher model can …