Work

Active Reward Learning

Year: 2014
Type: conference-paper
Abstract: While reward functions are an essential component of many robot learning methods, defining such functions remains a hard problem in many practical applications.For tasks such as grasping, there are no reliable success measures available.Defining reward functions by hand requires extensive task knowledge and often leads to undesired emergent behavior.Instead, we propose to learn the reward function through active learning, querying human expert knowledge for a subset of the agent's rollouts.We introduce a framework, wherein a traditional learning algorithm interplays with the reward learning component, such that the evolution of the action learner guides the queries of the reward learner.We demonstrate results of our method on a robot grasping task and show that the learned reward function generalizes to a similar task.
Language: English
Open Access status: bronze
OpenAlex ID: W218896052
FWCI: 2.797
Cites: 40
Cited by: 140
Related to: 9