Reward Shaping in Episodic Reinforcement Learning

Grzes, Marek (2017) Reward Shaping in Episodic Reinforcement Learning. In: Proc. of the 16th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2017). . pp. 565-573. ACM

Abstract

Recent advancements in reinforcement learning confirm that reinforcement learning techniques can solve large scale problems leading to high quality autonomous decision making. It is a matter of time until we will see large scale applications of reinforcement learning in various sectors, such as healthcare and cyber-security, among others. However, reinforcement learning can be time-consuming because the learning algorithms have to determine the long term consequences of their actions using delayed feedback or rewards. Reward shaping is a method of incorporating domain knowledge into reinforcement learning so that the algorithms are guided faster towards more promising solutions. Under an overarching theme of episodic reinforcement learning, this paper shows a unifying analysis of potential-based reward shaping which leads to new theoretical insights into reward shaping in both model-free and model-based algorithms, as well as in multi-agent reinforcement learning.

Item Type:	Conference or workshop item (Paper)
Uncontrolled keywords:	Reward structures for learning; Multiagent learning; Reward shaping; Reinforcement learning
Subjects:	Q Science > Q Science (General) > Q335 Artificial intelligence Q Science > QA Mathematics (inc Computing science) > QA273 Probabilities Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions:	Faculties > Sciences > School of Computing Faculties > Sciences > School of Computing > Computational Intelligence Group
Depositing User:	Marek Grzes
Date Deposited:	01 Mar 2017 09:22 UTC
Last Modified:	29 May 2019 18:45 UTC
Resource URI:	https://kar.kent.ac.uk/id/eprint/60614 (The current URI for this page, for reference purposes)