Zobrazeno 1 - 10
of 51
pro vyhledávání: '"Wu Faguo"'
Publikováno v:
Applied Mathematics and Nonlinear Sciences, Vol 9, Iss 1 (2024)
This paper combines blockchain technology with an information encryption algorithm to design a blockchain-based educational information protection model. It focuses on the role of Fabric architecture and blockchain data structure for information secu
Externí odkaz:
https://doaj.org/article/1cefb36f4ac743cd8b9cb2b692ae8bc6
In this paper, we investigate preference-based reinforcement learning (PbRL) that allows reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. Howeve
Externí odkaz:
http://arxiv.org/abs/2407.06503
Publikováno v:
International Journal of Intelligent Systems, Volume 2023
Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that utilize memory
Externí odkaz:
http://arxiv.org/abs/2402.04539
Mastering deep reinforcement learning (DRL) proves challenging in tasks featuring scant rewards. These limited rewards merely signify whether the task is partially or entirely accomplished, necessitating various exploration actions before the agent g
Externí odkaz:
http://arxiv.org/abs/2401.02225
The sparsity of reward feedback remains a challenging problem in online deep reinforcement learning (DRL). Previous approaches have utilized offline demonstrations to achieve impressive results in multiple hard tasks. However, these approaches place
Externí odkaz:
http://arxiv.org/abs/2401.00162
Publikováno v:
Knowledge-Based Systems 285 (2024) 111334
Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL. Most previo
Externí odkaz:
http://arxiv.org/abs/2312.16456
The normalization constraint on probability density poses a significant challenge for solving the Fokker-Planck equation. Normalizing Flow, an invertible generative model leverages the change of variables formula to ensure probability density conserv
Externí odkaz:
http://arxiv.org/abs/2309.15139
Publikováno v:
In Thermal Science and Engineering Progress September 2024 54
Publikováno v:
In Knowledge-Based Systems 15 February 2024 285
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.