Help an Agent Out: Student/Teacher Learning in Sequential Decision Tasks
نویسندگان
چکیده
Research on agents has led to the development of algorithms for learning from experience, accepting guidance from humans, and imitating experts. This paper explores a new direction for agents: the ability to teach other agents. In particular, we focus on situations where the teacher has limited expertise and instructs the student through action advice. The paper proposes and evaluates several teaching algorithms based on providing advice at a gradually decreasing rate. A crucial component of these algorithms is the ability of an agent to estimate its confidence in a state. We also contribute a student/teacher framework for implementing teaching strategies, which we hope will spur additional development in this relatively unexplored area.
منابع مشابه
Towards student/teacher learning in sequential decision tasks
Significant advances have been made in allowing agents to learn, both autonomously and with human guidance. However, less attention has been paid to the question of how agents could best teach each other. For instance, an existing robot in a factory should be able to instruct a newly arriving robot, even if it is from a different manufacturer, has a different knowledge representation, or is not...
متن کاملAgents Teaching Agents in Reinforcement Learning
Using reinforcement learning [4] (RL), agents can autonomously learn a control policy to master sequential-decision tasks. Rather than always learning tabula rasa, our recent work [5, 7, 8] considers how an experienced RL agent, the teacher, can help another RL agent, the student, to learn. As a motivating example, consider a household robot that has learned to perform tasks in a household. Whe...
متن کاملTeacher-Student Framework: A Reinforcement Learning Approach
We propose a reinforcement learning approach to learning to teach. Following Torrey and Taylor’s framework [18], an agent (the “teacher”) advises another one (the “student”) by suggesting actions the latter should take while learning a specific task in a sequential decision problem; the teacher is limited by a “budget” (the number of times such advice can be given). Our approach assumes a princ...
متن کاملAlgorithmic and Human Teaching of Sequential Decision Tasks
A helpful teacher can significantly improve the learning rate of a learning agent. Teaching algorithms have been formally studied within the field of Algorithmic Teaching. These give important insights into how a teacher can select the most informative examples while teaching a new concept. However the field has so far focused purely on classification tasks. In this paper we introduce a novel m...
متن کاملOnline Multi-Task Learning Using Biased Sampling
One of the long-standing challenges in Artificial Intelligence for goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for learning behavior in many goal-directed sequential tasks has been in the form of distillation based learning wherein a single student network learns from multiple task-specific teacher networks by mimickin...
متن کامل