Results 161 to 170 of about 7,880,220 (196)

Online Markov Decision Processes

Mathematics of Operations Research, 2009
We consider a Markov decision process (MDP) setting in which the reward function is allowed to change after each time step (possibly in an adversarial manner), yet the dynamics remain fixed. Similar to the experts setting, we address the question of how well an agent can do when compared to the reward achieved under the best stationary policy over ...
Eyal Even-Dar, Sham M. Kakade, Yishay Mansour   +2 more
openaire   +1 more source

On the Generation of Markov Decision Processes

Journal of the Operational Research Society, 1995
Summary: Comparisons of the performance of solution algorithms for Markov decision processes rely heavily on problem generators to provide sizeable sets of test problems. Existing generation techniques allow little control over the properties of the test problems and often result in problems which are not typical of real-world examples.
Archibald, T. W., McKinnon, K. I. M., Thomas, L. C.   +2 more
openaire   +2 more sources

Monotonicity in a Markov Decision Process

Mathematics of Operations Research, 1988
Concavity of optimal costs and monotonicity of optimal actions are established for a Markov decision problem in which state space and action space are ordered, but in which the cost functions do not possess properties commonly used to establish monotonicity.
openaire   +2 more sources

Evidential Markov Decision Processes

2011
This paper proposes a new model, the EMDP (Evidential Markov Decision Process). It is a MDP (Markov Decision Process) for belief functions in which rewards are defined for each state transition, like in a classical MDP, whereas the transitions are modeled as in an EMC (Evidential Markov Chain), i.e.
Hélène Soubaras, Christophe Labreuche, Pierre Savéant   +2 more
openaire   +2 more sources

Risk-Constrained Markov Decision Processes

IEEE Transactions on Automatic Control, 2010
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Vivek S. Borkar, Rahul Jain 0002
openaire   +4 more sources

Easy Affine Markov Decision Processes

Operations Research, 2019
Individuals, firms, and governments often face the challenge of making optimal decisions in a dynamic setting amidst a changing and uncertain environment. Although Markov decision processes (MDPs) provide a powerful modeling framework for such problems, solving an MDP is generally difficult.
Jie Ning, Matthew J. Sobel
openaire   +2 more sources

On constrained Markov decision processes

Operations Research Letters, 1996
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +3 more sources

Competing Markov decision processes

Annals of Operations Research, 1991
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +2 more sources

Variability sensitive Markov decision processes

Proceedings of the 28th IEEE Conference on Decision and Control, 1992
Considered are time-average Markov Decision Processes (MDPs) with finite state and action spaces. Two definitions of variability are introduced, namely, the expected time-average variability and time-average expected variability. The two criteria are in general different, although they can both be employed to penalize for variance in the stream of ...
Melike Baykal-Gürsoy, Keith W. Ross
openaire   +3 more sources

Coevolutive planning in markov decision processes

Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 2 - AAMAS '02, 2002
We investigate the idea of having groups of agents coevolving in order to iteratively refine multi-agent plans. This idea we called coevolution is formalized and analyzed in a general purpose and applied to the stochastic control frameworks that use an explicit model of the world\,: coevolution can directly be adapted to the frameworks of Multi-Agent ...
Scherrer, Bruno, Charpillet, François
openaire   +3 more sources