Picture for Istvan Szita

Istvan Szita

Exploring compact reinforcement-learning representations with linear regression

Add code
May 09, 2012
Figure 1 for Exploring compact reinforcement-learning representations with linear regression
Figure 2 for Exploring compact reinforcement-learning representations with linear regression
Figure 3 for Exploring compact reinforcement-learning representations with linear regression
Figure 4 for Exploring compact reinforcement-learning representations with linear regression
Viaarxiv icon

Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs - Extended Version

Add code
Apr 21, 2009
Viaarxiv icon

Factored Value Iteration Converges

Add code
Aug 13, 2008
Figure 1 for Factored Value Iteration Converges
Viaarxiv icon

Online variants of the cross-entropy method

Add code
Jan 14, 2008
Figure 1 for Online variants of the cross-entropy method
Figure 2 for Online variants of the cross-entropy method
Figure 3 for Online variants of the cross-entropy method
Viaarxiv icon

Reinforcement Learning with Linear Function Approximation and LQ control Converges

Add code
Mar 09, 2007
Figure 1 for Reinforcement Learning with Linear Function Approximation and LQ control Converges
Figure 2 for Reinforcement Learning with Linear Function Approximation and LQ control Converges
Figure 3 for Reinforcement Learning with Linear Function Approximation and LQ control Converges
Viaarxiv icon

Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs

Add code
Oct 30, 2006
Figure 1 for Low-complexity modular policies: learning to play Pac-Man and a new framework beyond MDPs
Viaarxiv icon

Kalman filter control in the reinforcement learning framework

Add code
Jan 09, 2003
Viaarxiv icon

Temporal plannability by variance of the episode length

Add code
Jan 09, 2003
Figure 1 for Temporal plannability by variance of the episode length
Figure 2 for Temporal plannability by variance of the episode length
Figure 3 for Temporal plannability by variance of the episode length
Figure 4 for Temporal plannability by variance of the episode length
Viaarxiv icon

Searching for Plannable Domains can Speed up Reinforcement Learning

Add code
Dec 10, 2002
Figure 1 for Searching for Plannable Domains can Speed up Reinforcement Learning
Figure 2 for Searching for Plannable Domains can Speed up Reinforcement Learning
Figure 3 for Searching for Plannable Domains can Speed up Reinforcement Learning
Figure 4 for Searching for Plannable Domains can Speed up Reinforcement Learning
Viaarxiv icon