Zobrazeno 1 - 10
of 3 333
pro vyhledávání: '"Viano A"'
We present a new algorithm for imitation learning in infinite horizon linear MDPs dubbed ILARL which greatly improves the bound on the number of trajectories that the learner needs to sample from the environment. In particular, we remove exploration
Externí odkaz:
http://arxiv.org/abs/2405.02181
In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of congestion games in the semi-bandit feedback setting. Our proposed method ad
Externí odkaz:
http://arxiv.org/abs/2306.15543
In online reinforcement learning (RL), instead of employing standard structural assumptions on Markov decision processes (MDPs), using a certain coverage condition (original from offline RL) is enough to ensure sample-efficient guarantees (Xie et al.
Externí odkaz:
http://arxiv.org/abs/2304.12886
Publikováno v:
AERA Open, Vol 10 (2024)
How scholars name different racial groups has powerful salience for understanding what researchers study. We explored how education researchers used racial terminology in recently published high-profile peer-reviewed studies. Our sample included 1,42
Externí odkaz:
https://doaj.org/article/84f53110c56d4d98bd19b871dfeadf6b
Publikováno v:
Frontiers in Education, Vol 9 (2024)
School systems have increasingly turned to continuous improvement (CI) processes because traditional school improvement plans (SIPs) have resulted in neither reaching set goals nor maintaining performance in challenging times. Improvement science is
Externí odkaz:
https://doaj.org/article/87071c7275c1479eb28ac269897418d6
While Reinforcement Learning (RL) aims to train an agent from a reward function in a given environment, Inverse Reinforcement Learning (IRL) seeks to recover the reward function from observing an expert's behavior. It is well known that, in general,
Externí odkaz:
http://arxiv.org/abs/2209.10974
This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and
Externí odkaz:
http://arxiv.org/abs/2209.10968
This paper provides a theoretical study of deep neural function approximation in reinforcement learning (RL) with the $\epsilon$-greedy exploration under the online setting. This problem setting is motivated by the successful deep Q-networks (DQN) fr
Externí odkaz:
http://arxiv.org/abs/2209.07376
Publikováno v:
Heliyon, Vol 10, Iss 18, Pp e37591- (2024)
Objective: The effect of ESC (Electronic Stability Control) was investigated for the rate of crash exposure, serious injury and fatality in pole and tree impacts. Field data was analyzed by crash type (front, side, rear and rollover) and model year (
Externí odkaz:
https://doaj.org/article/ad075658e60141c592405bb132ad9381
Publikováno v:
Frontiers in Blockchain, Vol 7 (2024)
Blockchain for local communities are blockchain-based applications that support the participation of people in the social and economic life of their local community. These applications leverage tokenization to enable socio-economic processes involvin
Externí odkaz:
https://doaj.org/article/694f14208b3d4759913da69b86333ebc