Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Ornia, Daniel Jarne"'
For an autonomous vehicle to operate reliably within real-world traffic scenarios, it is imperative to assess the repercussions of its prospective actions by anticipating the uncertain intentions exhibited by other participants in the traffic environ
Externí odkaz:
http://arxiv.org/abs/2402.17387
In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularization) to randomize their actions in favor of exploration. From a human perspective, this makes RL a
Externí odkaz:
http://arxiv.org/abs/2311.18703
Policy robustness in Reinforcement Learning may not be desirable at any cost: the alterations caused by robustness requirements from otherwise optimal policies should be explainable, quantifiable and formally verifiable. In this work we study how pol
Externí odkaz:
http://arxiv.org/abs/2209.15320
Autor:
Ornia, Daniel Jarne, Mazo Jr, Manuel
Publikováno v:
Formal Modeling and Analysis of Timed Systems. FORMATS 2022. Lecture Notes in Computer Science, vol 13465. Springer, Cham
We present an approach to reduce the communication required between agents in a Multi-Agent learning system by exploiting the inherent robustness of the underlying Markov Decision Process. We compute so-called robustness surrogate functions (off-line
Externí odkaz:
http://arxiv.org/abs/2204.03361
Autor:
Ornia, Daniel Jarne, Mazo Jr, Manuel
We present an approach to reduce the communication of information needed on a Distributed Q-Learning system inspired by Event Triggered Control (ETC) techniques. We consider a baseline scenario of a distributed Q-learning problem on a Markov Decision
Externí odkaz:
http://arxiv.org/abs/2109.01417
We present a biologically inspired design for swarm foraging based on ant's pheromone deployment, where the swarm is assumed to have very restricted capabilities. The robots do not require global or relative position measurements and the swarm is ful
Externí odkaz:
http://arxiv.org/abs/2105.10331
Collaborative multi-agent robotic systems where agents coordinate by modifying a shared environment often result in undesired dynamical couplings that complicate the analysis and experiments when solving a specific problem or task. Simultaneously, bi
Externí odkaz:
http://arxiv.org/abs/2103.07714
Autor:
Ornia, Daniel Jarne, Mazo, Manuel
Publikováno v:
2022 IEEE 61st Conference on Decision and Control (CDC)
We present an approach to reduce the communication of information needed on a Distributed Q-Learning system inspired by Event Triggered Control (ETC) techniques. We consider a baseline scenario of a distributed Q-learning problem on a Markov Decision
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::87f92ed119629124f90e685a8aed4084
https://doi.org/10.1109/cdc51059.2022.9992660
https://doi.org/10.1109/cdc51059.2022.9992660
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Policy robustness in Reinforcement Learning (RL) may not be desirable at any price; the alterations caused by robustness requirements from otherwise optimal policies should be explainable and quantifiable. Policy gradient algorithms that have strong
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7a40bb24c044208286bc6be6d6d4c24f