Sur les abstractions et les projections des processus décisionnels de Markov de grande taille

Abstract : Markov Decision Processes (MDP) are a mathematical formalism of many domains of artifical intelligence such as planning, machine learning, reinforcement learning... Solving an MDP means finding the optimal strategy or policy of an agent interacting in a stochastic environment. When the size of this system becomes very large it becomes hard to solve this problem with classical methods. This thesis deals with the resolution of MDPs with large state space. It studies some resolution methods such as: abstractions and the projection methods. It shows the limits of some approachs and identifies some structures that may be interesting for the MDP resolution. This thesis focuses also on projection methods, the Least square temporal difference algorithm LSTD([lambda]). An estimate of the rate of the convergence of this algorithm has been derived with an emphasis on the role played by the parameter [lambda]. This analysis has then been generalized to the case of Least square non stationary policy iteration LS([lambda])NSPI . We compute a performance bound for LS([lambda])NSPI by bounding the error between the value computed given a fixed iteration and the value computed under the optimal policy, that we aim to determine
Document type :
Theses
Complete list of metadatas

Cited literature [7 references]  Display  Hide  Download

https://hal.univ-lorraine.fr/tel-01751259
Contributor : Thèses Ul <>
Submitted on : Thursday, March 29, 2018 - 1:13:30 PM
Last modification on : Tuesday, April 24, 2018 - 1:30:06 PM

File

DDOC_T_2015_0005_TAGORTI.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : tel-01751259, version 1

Collections

Citation

Manel Tagorti. Sur les abstractions et les projections des processus décisionnels de Markov de grande taille. Autre [cs.OH]. Université de Lorraine, 2015. Français. ⟨NNT : 2015LORR0005⟩. ⟨tel-01751259⟩

Share

Metrics

Record views

40

Files downloads

42