Zobrazeno 1 - 10
of 824
pro vyhledávání: '"JONSSON, ANDERS"'
This work studies offline Reinforcement Learning (RL) in a class of non-Markovian environments called Regular Decision Processes (RDPs). In RDPs, the unknown dependency of future observations and rewards from the past interactions can be captured by
Externí odkaz:
http://arxiv.org/abs/2409.02747
We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike previous work, our approach allows learning low-level and high-level t
Externí odkaz:
http://arxiv.org/abs/2407.06690
Autor:
Carrascosa-Zamacois, Marc, Galati-Giordano, Lorenzo, Wilhelmi, Francesc, Fontanesi, Gianluca, Jonsson, Anders, Geraci, Giovanni, Bellalta, Boris
Extended Reality (XR) has stringent throughput and delay requirements that are hard to meet with current wireless technologies. Missing these requirements can lead to worsened picture quality, perceived lag between user input and corresponding output
Externí odkaz:
http://arxiv.org/abs/2407.05802
We propose a new framework for formulating optimal transport distances between Markov chains. Previously known formulations studied couplings between the entire joint distribution induced by the chains, and derived solutions via a reduction to dynami
Externí odkaz:
http://arxiv.org/abs/2406.04056
Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward specificatio
Externí odkaz:
http://arxiv.org/abs/2403.15301
Autor:
Steccanella, Lorenzo, Jonsson, Anders
This paper presents a state representation for reward-free Markov decision processes. The idea is to learn, in a self-supervised manner, an embedding space where distances between pairs of embedded states correspond to the minimum number of actions n
Externí odkaz:
http://arxiv.org/abs/2312.10276
Planning as heuristic search is one of the most successful approaches to classical planning but unfortunately, it does not extend trivially to Generalized Planning (GP). GP aims to compute algorithmic solutions that are valid for a set of classical p
Externí odkaz:
http://arxiv.org/abs/2301.11087
Autor:
Carrascosa-Zamacois, Marc, Geraci, Giovanni, Galati-Giordano, Lorenzo, Jonsson, Anders, Bellalta, Boris
Will Wi-Fi 7, conceived to support extremely high throughput, also deliver consistently low delay? The best hope seems to lie in allowing next-generation devices to access multiple channels via multi-link operation (MLO). In this paper, we aim to adv
Externí odkaz:
http://arxiv.org/abs/2210.07695