360 search results - page 8 / 72 » Combining Learned Discrete and Continuous Action Models |
FM
1999
Springer
15 years 1 months ago
1999
Springer
Support for system speci cation in terms of modelling and simulation environments has become a common practice in safety-critical applications. Also, a current trend is the automat...
AAAI
1996
14 years 10 months ago
1996
Overcoming the disadvantages of equidistant discretization of continuous actions, we introduce an approach that separates time into slices of varying length bordered by certain ev...
FUZZIEEE
2007
IEEE
15 years 3 months ago
2007
IEEE
— Reinforcement learning (RL) is a learning control paradigm that provides well-understood algorithms with good convergence and consistency properties. Unfortunately, these algor...
ICIA
2007
14 years 11 months ago
2007
Effective human-robot cooperation requires robotic devices that understand human goals and intentions. We frame the problem of intent recognition as one of tracking and predicting...
AIPS
2007
14 years 11 months ago
2007
This paper summarizes research on a new emerging framework for learning to plan using the Markov decision process model (MDP). In this paradigm, two approaches to learning to plan...