| Reinforcement Learning Toolbox |
| The
Reinforcemen Learning Toolbox: RL for optimal control Tasks
(Download
here) |
| The first part of
the thesis can be used as manual for the toolbox, the second part
contains benchmark tests for the used
algorithms.
|
|
|
Presentation as CI-Project (Download
here) |
| Powerpoint Slides
presenting some features of the
Toolbox.
|
|
|
| Interesting Papers |
| A (unfortunately quite old) list of papers concerning RL, needs
to be extended ...
|
| Actor Critic Learning |
|
Supervised learning combined with an actor-critic architecture
( by Rosensten, Barto)
(Download
here) |
|
|
| Continous State Learning |
| A
Fuzzy Reinforcement Function for the Intelligent Agent
( by Seo, Youn)
(Download
here) |
|
|
|
|
|
|
|
|
|
|
| General |
|
Incremental Reinforcement Learning
( by Dixon, Malok, Kohsla)
(Download
here) |
|
|
|
| ML - A
Comparison of different Algorithm.pdf
( by Mahedevan)
(Download
here) |
|
|
|
|
| Gradient Descent RL |
|
Reinforcement Learning Through Gradient Descent
( by Baird)
(Download
here) |
|
| Direct
Gradient-Based Reinforcement Learning
( by Baxter, Bartlett)
(Download
here) |
|
|
|
|
| Hierarichical Learning |
|
Hierarchical Reinforcement Learning: MAXQ
( by Gerhard Neumann)
(Download
here) |
| Powerpoint slides
for the Computational Intelligence Seminar A, WS 02, a short survey
about hierarchical RL, with emphasize to MAXQ
Learning
|
|
|
Discovering Hierarchy in Reinforcement Learning with HEXQ
( by Hengst)
(Download
here) |
|
|
Learning Hierarchical Decomposition for Factored MDPs
( by Hengst)
(Download
here) |
|
|
Hierarchical Multi-Agent Reinforcement Learning
( by Mahedevan)
(Download
here) |
|
| State
Abstraction for Programmable Reinforcement Learning Agents
( by Andre, Russel)
(Download
here) |
|
|
|
|
Multiagent Planning with Factored MDPs
( by Guestrin, Koller, Parr)
(Download
here) |
|
|
Hierarchical Memory-based Reinforcement Learning
( by Fernandez-Gardiol, Mahedevan)
(Download
here) |
|
|
Learning to Use Selective Attention and Short-Term Memory in
Sequential Tasks
( by McCallum)
(Download
here) |
|
|
Hierarchical Reinforcement Learning with the MAXQ Value Function
Decomposition
( by Dietterich)
(Download
here) |
|
|
| High Dimensionality |
|
|
| Model Based RL |
|
Generalized Prioritized Sweeping
( by Andre, Friedman, Parr)
(Download
here) |
|
|
| Prior Knowledge |
| Using
Background Knowledge
( by Shapiro, Langley, Shachter)
(Download
here) |
|
|
| Robocup |
|
|
|
|
|
Scaling Reinfocrement Learning Towards Robocup
( by Stone, Sutton)
(Download
here) |
|
|
|
|
