Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

7

NIPS
2000

favoriteEmaildiscussreport

112views Information Technology» more NIPS 2000»

Balancing Multiple Sources of Reward in Reinforcement Learning

13 years 5 months ago

Balancing Multiple Sources of Reward in Reinforcement Learning

Download www.cc.gatech.edu

For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems include agents with multiple goals and agents with multiple users. Creating a single reward value by combining the multiple components can throw away vital information and can lead to incorrect solutions. We describe the multiple reward source problem and discuss the problems with applying traditional reinforcement learning. We then present an new algorithm for finding a solution and results on simulated environments.

Christian R. Shelton

Real-time Traffic

Multiple Scalar Components | NIPS 2000 | NIPS 2007 | Reinforcement Learning | Single Scalar Value |

claim paper

Related Content

» Exploiting Multiple Secondary Reinforcers in Policy Gradient Reinforcement Learning

» Automatic shaping and decomposition of reward functions

» Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled ...

» MultiAgent Inverse Reinforcement Learning

» A social reinforcement learning agent

» Reinforcement learning with limited reinforcement using Bayes risk for active learning in ...

» Learning all optimal policies with multiple criteria

» Online evolutionary computation for reinforcement learning in stochastic domains

» A kNN Based Perception Scheme for Reinforcement Learning

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	2000
Where	NIPS
Authors	Christian R. Shelton

Comments (0)