NDLI: Active reward learning with a novel acquisition function

Content Provider	Springer Nature Link
Author	Daniel, Christian Kroemer, Oliver Viering, Malte Metz, Jan Peters, Jan
Copyright Year	2015
Abstract	Reward functions are an essential component of many robot learning methods. Defining such functions, however, remains hard 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. We introduce a framework, wherein the robot simultaneously learns an action policy and a model of the reward function by actively querying a human expert for ratings. We represent the reward model using a Gaussian process and evaluate several classical acquisition functions (AFs) from the Bayesian optimization literature in this context. Furthermore, we present a novel AF, expected policy divergence. We demonstrate results of our method for a robot grasping task and show that the learned reward function generalizes to a similar task. Additionally, we evaluate the proposed novel AF on a real robot pendulum swing-up task.
Starting Page	389
Ending Page	405
Page Count	17
File Format	PDF
ISSN	09295593
Journal	Autonomous Robots
Volume Number	39
Issue Number	3
e-ISSN	15737527
Language	English
Publisher	Springer US
Publisher Date	2015-07-16
Publisher Place	New York
Access Restriction	One Nation One Subscription (ONOS)
Subject Keyword	Reinforcement learning Active learning Bayesian optimization Preference learning Inverse reinforcement learning Reward functions Acquisition functions Robotics and Automation Artificial Intelligence (incl. Robotics) Computer Imaging, Vision, Pattern Recognition and Graphics Control, Robotics, Mechatronics
Content Type	Text
Resource Type	Article
Subject	Artificial Intelligence

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Learning state representations with robotic priors

Discovering relevant task spaces using inverse feedback control

Learning the behavior model of a robot

Efficient vision-based navigation : Learning about the influence of motion blur

Reinforcement learning to adjust parametrized motor primitives to new situations

DCOB: Action space for reinforcement learning of high DoF robots

Dynamic Bayesian network for semantic place classification in mobile robotics

From human to humanoid locomotion—an inverse optimal control approach

Robot life-long task learning from human demonstrations: a Bayesian approach

Active reward learning with a novel acquisition function

Similar Documents

Learning state representations with robotic priors

Discovering relevant task spaces using inverse feedback control

Learning the behavior model of a robot

Efficient vision-based navigation : Learning about the influence of motion blur

Reinforcement learning to adjust parametrized motor primitives to new situations

DCOB: Action space for reinforcement learning of high DoF robots

Dynamic Bayesian network for semantic place classification in mobile robotics

From human to humanoid locomotion—an inverse optimal control approach

Robot life-long task learning from human demonstrations: a Bayesian approach

Active reward learning with a novel acquisition function