Predictive Memory for an inaccessible environment
- Michael Bowling, University of Alberta
- Peter Stone, Department of Computer Sciences, The University of Texas at Austin
- Manuela Veloso
Inaccessible and nondeterministic environ- ments are very common in real-world problems. One of the diculties in these environments is representing the knowledge about the unknown aspects of the state. We present a solution to this problem for the robotic soccer domain, an inaccessible and nondeterministic environment. We developed a predictive memory model that builds a probabilistic representation of the state based on past observations. By making the right assumptions, an eective model can be created that can store and update knowledge for even the inaccessible parts of the environ- ment. Experiments were conducted to compare the eectiveness of our approach with a simpler approach, which ignored the inaccessible parts of the environment. The experiments consisted of using the memory models in a situation of a free ball, where two players are racing af- ter the ball to be the rst to pass it or kick it to one of their teammates or the goal. The results obtained demonstrate that this predic- tive approach does generate an eective mem- ory model, which outperforms a non-predictive model.
Citation
M. Bowling, P. Stone, M. Veloso. "Predictive Memory for an inaccessible environment". RoboCup, November 1996.Keywords: | |
Category: | In Workshop |
BibTeX
@misc{Bowling+al:RoboCup96, author = {Michael Bowling and Peter Stone and Manuela Veloso}, title = {Predictive Memory for an inaccessible environment}, Booktitle = {Working Notes of the IROS-96 workshop on RoboCup}, booktitle = {}, year = 1996, }Last Updated: March 09, 2007
Submitted by AICML Admin Assistant