Back to results
University of Illinois at Urbana-Champaign
Theory and Application of Reward Shaping in Reinforcement Learning
Abstract
dc:descriptionWe demonstrate our theory with two applications: a stochastic gridworld, and a bipedal walking control task. In all cases, the experiments uphold the analytical predictions; most notably that reducing the reward horizon implies faster learning. The bipedal walking task demonstrates that our reward shaping techniques allow a conventional reinforcement learning algorithm to find a good behavior efficiently despite a large state space with stochastic actions.
Degree
thesis:*- Name thesis:degree_name
- Ph.D.
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Computer Science
- Grantor
- University of Illinois at Urbana-Champaign
- Year dc:date
- 2015
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Laud, Adam Daniel
- Contributors dc:contributor
-
- Gerald DeJong
Subjects
dc:subject × 1Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- (MiAaPQ)AAI3130966
- OAI identifier oai:identifier
- oai:www.ideals.illinois.edu:2142/81640