Reinforcement learning for crop management support: Review, prospects and challenges

Autor: Romain Gautron, Odalric-Ambrym Maillard, Philippe Preux, Marc Corbeels, Régis Sabbadin

Publikováno v: Computers and Electronics in Agriculture

Reinforcement learning (RL), including multi-armed bandits, is a branch of machine learning that deals with the problem of sequential decision-making in uncertain and unknown environments through learning by practice. While best known for being the c

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::772dbc4942690393979f89fbf33b2e50
http://agritrop.cirad.fr/601655/

A channel selection game for multi-operator LoRaWAN deployments

Autor: Kinda Khawam, Hassan Fawaz, Samer Lahoud, Odalric-Ambrym Maillard, Steven Martin

Publikováno v: Computer Networks
Computer Networks, 2022, 216, pp.109185. ⟨10.1016/j.comnet.2022.109185⟩

With over 75 billion Internet of Things (IoT) devices expected worldwide by the year 2025, inaugural MAC layer solutions for long-range IoT deployments no longer suffice. LoRaWAN, the principal technology for comprehensive IoT deployments, enables lo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ac8ecf050216593bbf1df50d5f755bff
https://doi.org/10.1016/j.comnet.2022.109185

Boundary Crossing Probabilities for General Exponential Families

Autor: Odalric-Ambrym Maillard

Publikováno v: Mathematical Methods of Statistics
Mathematical Methods of Statistics, 2018, 27, pp.1-31. ⟨10.3103/S1066530718010015⟩
Mathematical Methods of Statistics, Allerton Press, Springer (link), 2018, 27
Mathematical Methods of Statistics, Allerton Press, Springer (link), 2018, 27, pp.1-31. ⟨10.3103/S1066530718010015⟩

We consider parametric exponential families of dimension K on the real line. We study a variant of boundary crossing probabilities coming from the multi-armed bandit literature, in the case when the real-valued distributions form an exponential famil

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::448656e8ec79694d6afb05e9cee4115f
https://hal.science/hal-01737150/document

Practical Open-Loop Optimistic Planning

Autor: Edouard Leurent, Odalric-Ambrym Maillard

Publikováno v: Machine Learning and Knowledge Discovery in Databases ISBN: 9783030461324
ECML/PKDD (3)
European Conference on Machine Learning
European Conference on Machine Learning, Sep 2019, Würzburg, Germany

International audience; We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies-i.e. sequences of actions-and under budget constraint. In this setting, the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3a3a2b433597e42f60776f180b1fef0d
http://arxiv.org/abs/1904.04700

Selecting Near-Optimal Approximate State Representations in Reinforcement Learning

Autor: Daniil Ryabko, Ronald Ortner, Odalric-Ambrym Maillard

Publikováno v: International Conference on Algorithmic Learning Theory (ALT)
International Conference on Algorithmic Learning Theory (ALT), Oct 2014, Bled, Slovenia. pp.140-154
Lecture Notes in Computer Science ISBN: 9783319116617
ALT

We consider a reinforcement learning setting introduced in (Maillard et al., NIPS 2011) where the learner does not have explicit access to the states of the underlying Markov decision process (MDP). Instead, she has access to several models that map

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::118a0cd174f76142e45e7ec738e8e62a
https://inria.hal.science/hal-01057562