Hidden State and Reinforcement Learning with Instance-Based State Identification  (Make Corrections)  (19 citations)
R. Andrew McCallum

  Home/Search   Context   Related

 
View or download:
rochester.edu/pub/...lumnsmieee.ps.gz
rochester.edu/robo...mccallumieee.ps.Z
rochester.edu/pub/...mccallumieee.ps.Z
Cached:  PS.gz  PS  PDF   Image  Update  Help
Problem Downloading?
From:  rochester.edu/u/mccallum/ (more)
From:  rochester.edu
(Enter author homepages)

Rate this article: (best)
  Comment on this article  
(Enter summary)

Abstract: Real robots with real sensors are not omniscient. When a robot's next course of action depends on information that is hidden from the sensors because of problems such as occlusion, restricted range, bounded field of view and limited attention, we say the robot suffers from the hidden state problem. State identification techniques use history information to uncover hidden state. Some previous approaches to encoding history include: finite state machines [12, 28], recurrent neural networks [25]... (Update)

Similar documents based on text:   More   All
0.2:   Object Consolodation by Graph Partitioning with a.. - McCallum, Wellner (2003)   (Correct)
0.2:   Uncovered Interest Parity and Policy Behavior New Evidence - Christensen   (Correct)
0.2:   Reduced Training Time for Reinforcement Learning with Hidden State - McCallum (1994)   (Correct)

BibTeX entry:   (Update)

McCallum, A. K. (1996a). Hidden state and reinforcement learning with instance-based state identification. http://citeseer.ist.psu.edu/32765.html   More

@misc{ mccallum-hidden,
  author = "A. McCallum",
  title = "Hidden state and reinforcement learning with instance-based state identification",
  text = "McCallum, A. K. (1996a). Hidden state and reinforcement learning with instance-based
    state identification.",
  url = "citeseer.ist.psu.edu/32765.html" }
Citations (may not include all citations):
2489   Maximum likelihood from incomplete data via the EM algorithm (context) - Dempster, Laird et al. - 1977
2111   Pattern Classification and Scene Analysis (context) - Duda, Hart - 1973
1905   Adaptation in natural and artificial systems (context) - Holland - 1975
1332   A tutorial on hidden Markov models and selected applications.. (context) - Rabiner - 1989  ACM
1023   Genetic Programming: On the Programming of Computers by Mean.. (context) - Koza - 1992
641   Learning from delayed rewards (context) - Watkins - 1989
148   Acting optimally in partially observable stochastic domains - Cassandra, Kaelbling et al. - 1994
125   Learning and sequential decision making - Barto, Sutton et al. - 1990
115   The parti-game algorithm for variable resolution reinforceme.. - Moore - 1993
106   Outline for a theory of intelligence (context) - Albus - 1991
102   Reinforcement learning with perceptual aliasing: The percept.. - Chrisman - 1992
100   Reinforcement Learning for Robots Using Neural Networks (context) - Lin - 1993
95   Classifier systems and genetic algorithms (context) - Booker, Goldberg et al. - 1989
83   Neuron-like elements that can solve difficult learning contr.. (context) - Barto, Sutton et al. - 1983
83   Real-time learning and control using asynchronous dynamic pr.. (context) - Barto, Bradtke et al. - 1991

[Article contains additional citations not shown here]



The graph only includes citing articles where the year of publication is known.


Documents on the same site (http://www.cs.rochester.edu/u/mccallum/):   More
Overcoming Incomplete Perception with Utile Distinction Memory - McCallum (1993)   (Correct)
Learning to Use Selective Attention and Short-Term Memory in.. - McCallum (1996)   (Correct)
Short-Term Memory in Visual Routines for "Off-Road Car Chasing" - Andrew Mccallum   (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