-
Metrics for Finite Markov Decision Processes
We present metrics for measuring the similarity of states in a finite Ma...
07/11/2012 ∙ by Norman Ferns, et al. ∙
0
∙
share
read it
-
Scalable methods for computing state similarity in deterministic Markov Decision Processes
We present new algorithms for computing and approximating bisimulation m...
11/21/2019 ∙ by Pablo Samuel Castro, et al. ∙
49
∙
share
read it
-
Efficient Planning in Large MDPs with Weak Linear Function Approximation
Large-scale Markov decision processes (MDPs) require planning algorithms...
07/13/2020 ∙ by Roshan Shariff, et al. ∙
0
∙
share
read it
-
An Approximate Solution Method for Large Risk-Averse Markov Decision Processes
Stochastic domains often involve risk-averse decision makers. While rece...
10/16/2012 ∙ by Marek Petrik, et al. ∙
0
∙
share
read it
-
Stability-Constrained Markov Decision Processes Using MPC
In this paper, we consider solving discounted Markov Decision Processes ...
02/02/2021 ∙ by Mario Zanon, et al. ∙
0
∙
share
read it
-
Max-Plus Matching Pursuit for Deterministic Markov Decision Processes
We consider deterministic Markov decision processes (MDPs) and apply max...
06/20/2019 ∙ by Francis Bach, et al. ∙
1
∙
share
read it
-
Model Reduction Techniques for Computing Approximately Optimal Solutions for Markov Decision Processes
We present a method for solving implicit (factored) Markov decision proc...
02/06/2013 ∙ by Thomas L. Dean, et al. ∙
0
∙
share
read it
Metrics for Markov Decision Processes with Infinite State Spaces
07/04/2012 ∙ by Norman Ferns, et al. ∙
0
∙
share
We present metrics for measuring state similarity in Markov decision processes (MDPs) with infinitely many states, including MDPs with continuous state spaces. Such metrics provide a stable quantitative analogue of the notion of bisimulation for MDPs, and are suitable for use in MDP approximation. We show that the optimal value function associated with a discounted infinite horizon planning task varies continuously with respect to our metric distances.
READ FULL TEXT
Comments
There are no comments yet.