NDLI: Free energy based policy gradients

Content Provider	IEEE Xplore Digital Library
Author	Theodorou, E.A. Najemnik, J. Todorov, E.
Copyright Year	2013
Description	Author affiliation: Depts. of Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA (Todorov, E.) \|\| Dept. of Comput. Sci. & Eng., Univ. of Washington, Seattle, WA, USA (Theodorou, E.A.) \|\| Appl. Math, Univ. of Washington, Seattle, WA, USA (Najemnik, J.)
Abstract	Despite the plethora of reinforcement learning algorithms in machine learning and control, the majority of the work in this area relies on discrete time formulations of stochastic dynamics. In this work we present a new policy gradient algorithm for reinforcement learning in continuous state action spaces and continuous time for free energy-like cost functions. The derivation is based on successive application of Girsanov's theorem and the use of the Radon Nikodým derivative as formulated for Markov diffusion processes. The resulting policy gradient is reward weighted. The use of Radon Nikodým extends analysis and results to more general models of stochasticity in which jump diffusions processes are considered. We apply the resulting algorithm in two simple examples for learning attractor landscapes in rhythmic and discrete movements.
Starting Page	124
Ending Page	131
File Size	274497
Page Count	8
File Format	PDF
ISBN	9781467359252
ISSN	23251824
DOI	10.1109/ADPRL.2013.6614998
Language	English
Publisher	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher Date	2013-04-16
Publisher Place	Singapore
Access Restriction	Subscribed
Rights Holder	Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subject Keyword	Heuristic algorithms Diffusion processes Learning (artificial intelligence) Markov processes Cost function Equations
Content Type	Text
Resource Type	Article

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

Solutions to finite horizon cost problems using actor-critic reinforcement learning

Average cost temporal-difference learning

Heuristics for multiagent reinforcement learning in decentralized decision problems

Model-based multi-objective reinforcement learning

Exponential moving average Q-learning algorithm

The Q(λ) algorithm based on heuristic reward function

Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning

Learning control of a bioreactor system using kernel-based heuristic dynamic programming

Reinforcement learning based secondary user transmissions in cognitive radio networks

Free energy based policy gradients

Similar Documents

Solutions to finite horizon cost problems using actor-critic reinforcement learning

Average cost temporal-difference learning

Heuristics for multiagent reinforcement learning in decentralized decision problems

Model-based multi-objective reinforcement learning

Exponential moving average Q-learning algorithm

The Q(λ) algorithm based on heuristic reward function

Nonparametric Bayesian reward segmentation for skill discovery using inverse reinforcement learning

Learning control of a bioreactor system using kernel-based heuristic dynamic programming

Reinforcement learning based secondary user transmissions in cognitive radio networks

Free energy based policy gradients