On Amount and Quality of Bias in Reinforcement Learning (ResearchIndex)

See this document in CiteSeerX!

On Amount and Quality of Bias in Reinforcement Learning (Make Corrections)
G. Hailu, G. Sommer

View or download:
ks.informatik.unikiel.de...smc99.ps.gz
Cached: PS.gz PS PDF Image Update Help

From: ks.informatik.uni...publications (more)
(Enter author homepages)

Rate this article:

(best)
Comment on this article

(Enter summary)
Abstract: Reinforcement learning is widely regarded as elegant in theory but hopelessly slow in practice. This is because it is often studied under the assumption that there is little or no prior information about the task at hand. This assumption, however, is not the defining characteristic of learning. Learning involves the incorporation of prior knowledge or bias that can greatly accelerates or otherwise improves the learning process. In this paper we address the influence of the amount and quality... (Update)

Active bibliography (related documents): More All
0.5: Real-Time Robot Learning - Bhanu, Leang, Cowden, Lin, Patterson (2001) (Correct)
0.3: Learning To Solve Markovian Decision Processes - Singh (1994) (Correct)
0.3: Continual Robot Learning with Constructive Neural Networks - Großmann, Poli (1998) (Correct)

Similar documents based on text: More All
0.1: Integrating Symbolic Knowledge in Reinforcement Learning - Hailu, Sommer (1998) (Correct)
0.1: Learning by Biasing - Hailu, Sommer (1998) (Correct)
0.1: Embedding Knowledge in Reinforcement Learning - Hailu, Sommer (1998) (Correct)

BibTeX entry: (Update)

@misc{ hailu-amount,
  author = "G. Hailu and G. Sommer",
  title = "On Amount and Quality of Bias in Reinforcement Learning",
  url = "citeseer.ist.psu.edu/309582.html" }

Citations (may not include all citations):
658 Learning from Delayed Rewards (context) - Watkins - 1989
563 Learning to predict by the methods of temporal differences - Sutton - 1988
257 Learning to act using real time dynamic programming - Barto, Bradtke et al. - 1995
138 an integrated architecture for learning (context) - Sutton, with - 1992
26 Reinforcement Learning for Robots Using Neural Networks (context) - Lin - 1993
25 Connectionist learning for control (context) - Barto - 1992
18 Automatic programming of behavior-based robots using reinfor.. (context) - Mahadevan, Connell - 1992
9 Reward functions for accelerated learning - Mataric - 1994
9 Using transitional proximity for faster reinforcement learni.. (context) - McCallum - 1992
3 A comparative analysis of reinforcement learning methods - Mataric - 1991
3 Artificial Intelligence Research (context) - Kaelbling, Littman et al. - 1996
2 Embedding knowledge in reinforcement learning - Hailu, Sommer - 1998
1 safe and incremental learning of navigation stratagies (context) - Millan - 1996

Documents on the same site (http://www.ks.informatik.uni-kiel.de/publications.html): More
Quaternionic Gabor Filters for Local Structure Classification - Bülow, Sommer (1998) (Correct)
Computing 3D Projective Invariants from Points and Lines - Lasenby, Bayro-Corrochano (1997) (Correct)
Hand-Eye Calibration in terms of motion of lines.. - Bayro-Corrochano, .. (Correct)

Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback

CiteSeer.IST - Copyright Penn State and NEC