Sciweavers

55 search results - page 2 / 11
» Intra-Option Learning about Temporally Abstract Actions
Sort
View
FMCO
2004
Springer
157views Formal Methods» more  FMCO 2004»
13 years 10 months ago
MoMo: A Modal Logic for Reasoning About Mobility
Abstract. A temporal logic is proposed as a tool for specifying properties of Klaim programs. Klaim is an experimental programming language that supports a programming paradigm whe...
Rocco De Nicola, Michele Loreti
NIPS
2003
13 years 6 months ago
Approximate Planning in POMDPs with Macro-Actions
Recent research has demonstrated that useful POMDP solutions do not require consideration of the entire belief space. We extend this idea with the notion of temporal abstraction. ...
Georgios Theocharous, Leslie Pack Kaelbling
IWANN
1999
Springer
13 years 9 months ago
Using Temporal Neighborhoods to Adapt Function Approximators in Reinforcement Learning
To avoid the curse of dimensionality, function approximators are used in reinforcement learning to learn value functions for individual states. In order to make better use of comp...
R. Matthew Kretchmar, Charles W. Anderson
ECCV
2010
Springer
13 years 8 months ago
Modeling Temporal Structure of Decomposable Motion Segments for Activity Classification
Abstract. Much recent research in human activity recognition has focused on the problem of recognizing simple repetitive (walking, running, waving) and punctual actions (sitting up...
ML
1998
ACM
220views Machine Learning» more  ML 1998»
13 years 4 months ago
Learning to Improve Coordinated Actions in Cooperative Distributed Problem-Solving Environments
Abstract. Coordination is an essential technique in cooperative, distributed multiagent systems. However, sophisticated coordination strategies are not always cost-effective in all...
Toshiharu Sugawara, Victor R. Lesser