4 search results - page 1 / 1 » Targeting Specific Distributions of Trajectories in MDPs |
AAAI
2006
13 years 7 months ago
2006
We define TTD-MDPs, a novel class of Markov decision processes where the traditional goal of an agent is changed from finding an optimal trajectory through a state space to realiz...
AAAI
2007
13 years 7 months ago
2007
In designing Markov Decision Processes (MDP), one must define the world, its dynamics, a set of actions, and a reward function. MDPs are often applied in situations where there i...
AIPS
2009
13 years 6 months ago
2009
When modeling real-world decision-theoretic planning problems in the Markov decision process (MDP) framework, it is often impossible to obtain a completely accurate estimate of tr...
ATAL
2007
Springer
13 years 11 months ago
2007
Springer
In this paper, we discuss the use of Targeted Trajectory Distribution Markov Decision Processes (TTD-MDPs)—a variant of MDPs in which the goal is to realize a specified distrib...