Learning to Teach Reinforcement Learning Agents

2017-07-28 · Anestis Fachantidis, Matthew E. Taylor, Ioannis Vlahavas

In this article we study the transfer learning model of action advice under a budget. We focus on reinforcement learning teachers providing action advice to heterogeneous students playing the game of Pac-Man under a limited advice budget. First, we examine several critical factors affecting advice quality in this setting, such as the average performance of the teacher, its variance and the importance of reward discounting in advising. The experiments show the non-trivial importance of the coefficient of variation (CV) as a statistic for choosing policies that generate advice. The CV statistic relates variance to the corresponding mean. Second, the article studies policy learning for distributing advice under a budget. Whereas most methods in the relevant literature rely on heuristics for advice distribution we formulate the problem as a learning one and propose a novel RL algorithm capable of learning when to advise, adapting to the student and the task at hand. Furthermore, we argue that learning to advise under a budget is an instance of a more generic learning problem: Constrained Exploitation Reinforcement Learning.

📄 PDF Abstract BibTeX arXiv:1707.09079

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Agent-Agnostic Human-in-the-Loop Reinforcement Learning

2017-01-15 · David Abel, John Salvatier, Andreas Stuhlmüller, Owain Evans

Providing Reinforcement Learning agents with expert advice can dramatically improve various aspects of learning. Prior work has developed teaching protocols that enable agents to learn efficiently in complex environments…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Learning to Teach in Cooperative Multiagent Reinforcement Learning

2018-05-20 · Shayegan Omidshafiei, Dong-Ki Kim, Miao Liu, Gerald Tesauro 외

Collective human knowledge has clearly benefited from the fact that innovations by individuals are taught to others through communication. Similar to human social groups, agents in distributed learning systems would like…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Policy composition in reinforcement learning via multi-objective policy optimization

2023-08-29 · Shruti Mishra, Ankit Anand, Jordan Hoffmann, Nicolas Heess 외

We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teacher policies are introduced as objectives, in addition to the task objective, in …

reinforcement-learning Reinforcement Learning

Autonomous Vehicle Fleet Coordination With Deep Reinforcement Learning

2018-01-01 · ICLR 2018 1 · Cane Punma

Autonomous vehicles are becoming more common in city transportation. Companies will begin to find a need to teach these vehicles smart city fleet coordination. Currently, simulation based modeling along with hand coded…

Autonomous Vehicles Decision Making Deep Reinforcement Learning Q-Learning+4

Online Transfer Learning in Reinforcement Learning Domains

2015-07-02 · Yusen Zhan, Matthew E. Taylor

This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1