| 2007 |
|---|
| 10 | EE | Bernhard Hengst:
Safe State Abstraction and Reusable Continuing Subtasks in Hierarchical Reinforcement Learning.
Australian Conference on Artificial Intelligence 2007: 58-67 |
| 2005 |
|---|
| 9 | EE | Robert Fitch,
Bernhard Hengst,
Dorian Suc,
Gregory Calbert,
Jason B. Scholz:
Structural Abstraction Experiments in Reinforcement Learning.
Australian Conference on Artificial Intelligence 2005: 164-175 |
| 2004 |
|---|
| 8 | EE | Bernhard Hengst:
Model Approximation for HEXQ Hierarchical Reinforcement Learning.
ECML 2004: 144-155 |
| 7 | EE | Duncan Potts,
Bernhard Hengst:
Discovering multiple levels of a task hierarchy concurrently.
Robotics and Autonomous Systems 49(1-2): 43-55 (2004) |
| 2002 |
|---|
| 6 | | Bernhard Hengst:
Discovering Hierarchy in Reinforcement Learning with HEXQ.
ICML 2002: 243-250 |
| 2001 |
|---|
| 5 | EE | Bernhard Hengst,
Darren Ibbotson,
Son Bao Pham,
Claude Sammut:
Omnidirectional Locomotion for Quadruped Robots.
RoboCup 2001: 368-373 |
| 4 | EE | Spencer Chen,
Martin Siu,
Thomas Vogelgesang,
Tak Fai Yik,
Bernhard Hengst,
Son Bao Pham,
Claude Sammut:
The UNSW RoboCup 2001 Sony Legged Robot League Team.
RoboCup 2001: 39-48 |
| 3 | EE | Son Bao Pham,
Bernhard Hengst,
Darren Ibbotson,
Claude Sammut:
Stochastic Gradient Descent Localisation in Quadruped Robots.
RoboCup 2001: 447-452 |
| 2000 |
|---|
| 2 | | Bernhard Hengst:
Generating Hierarchical Structure in Reinforcement Learning from State Variables.
PRICAI 2000: 533-543 |
| 1 | EE | Bernhard Hengst,
Darren Ibbotson,
Son Bao Pham,
John Dalgiesh,
Mike Lawther,
Phil Preston,
Claude Sammut:
The UNSW RoboCup 2000 Sony Legged League Team.
RoboCup 2000: 64-75 |
