Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Croissant, Lorenzo"'
We consider the Reinforcement Learning problem of controlling an unknown dynamical system to maximise the long-term average reward along a single trajectory. Most of the literature considers system interactions that occur in discrete time and discret
Externí odkaz:
http://arxiv.org/abs/2309.02815
Motivated by the design of fast reinforcement learning algorithms, we study the diffusive limit of a class of pure jump ergodic stochastic control problems. We show that, whenever the intensity of jumps is large enough, the approximation error is gov
Externí odkaz:
http://arxiv.org/abs/2209.15284
We consider the diffusive limit of a typical pure-jump Markovian control problem as the intensity of the driving Poisson process tends to infinity. We show that the convergence speed is provided by the H\"older constant of the Hessian of the limit pr
Externí odkaz:
http://arxiv.org/abs/2106.12848
In display advertising, a small group of sellers and bidders face each other in up to 10 12 auctions a day. In this context, revenue maximisation via monopoly price learning is a high-value problem for sellers. By nature, these auctions are online an
Externí odkaz:
http://arxiv.org/abs/2010.10070
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
International Conference on Machine Learning 2020
International Conference on Machine Learning 2020, Jul 2020, Vienna, Austria
International Conference on Machine Learning 2020, Jul 2020, Vienna, Austria
International audience; In display advertising, a small group of sellers and bidders face each other in up to 10 12 auctions a day. In this context, revenue maximisa-tion via monopoly price learning is a high-value problem for sellers. By nature, the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::2a8e20f1c702385e7b35114563a9e224
https://hal.archives-ouvertes.fr/hal-02971118
https://hal.archives-ouvertes.fr/hal-02971118