Zobrazeno 1 - 10
of 132
pro vyhledávání: '"Weng, Paul"'
Data augmentation is widely applied and has shown its benefits in different machine learning tasks. However, as recently observed in some downstream tasks, data augmentation may introduce an unfair impact on classifications. While it can improve the
Externí odkaz:
http://arxiv.org/abs/2407.03146
Various data augmentation techniques have been recently proposed in image-based deep reinforcement learning (DRL). Although they empirically demonstrate the effectiveness of data augmentation for improving sample efficiency or generalization, which t
Externí odkaz:
http://arxiv.org/abs/2402.12181
Recently, deep reinforcement learning has shown promising results for learning fast heuristics to solve routing problems. Meanwhile, most of the solvers suffer from generalizing to an unseen distribution or distributions with different scales. To add
Externí odkaz:
http://arxiv.org/abs/2402.02317
Autor:
Jiang, Zhaohui, Weng, Paul
To improve the sample efficiency of vision-based deep reinforcement learning (RL), we propose a novel method, called SPIRL, to automatically extract important patches from input images. Following Masked Auto-Encoders, SPIRL is based on Vision Transfo
Externí odkaz:
http://arxiv.org/abs/2402.03329
Reinforcement learning from human feedback (RLHF) is a variant of reinforcement learning (RL) that learns from human feedback instead of relying on an engineered reward function. Building on prior work on the related setting of preference-based reinf
Externí odkaz:
http://arxiv.org/abs/2312.14925
When applying reinforcement learning (RL) to a new problem, reward engineering is a necessary, but often difficult and error-prone task a system designer has to face. To avoid this step, we propose LR4GPM, a novel (deep) RL method that can optimize a
Externí odkaz:
http://arxiv.org/abs/2303.09027
Autor:
Glanois, Claire, Feng, Xuening, Jiang, Zhaohui, Weng, Paul, Zimmer, Matthieu, Li, Dong, Liu, Wulong
We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems. In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order rules are invented by learning e
Externí odkaz:
http://arxiv.org/abs/2112.13418
Autor:
Glanois, Claire, Weng, Paul, Zimmer, Matthieu, Li, Dong, Yang, Tianpei, Hao, Jianye, Liu, Wulong
Although deep reinforcement learning has become a promising machine learning approach for sequential decision-making problems, it is still not mature enough for high-stake domains such as autonomous driving or medical applications. In such contexts,
Externí odkaz:
http://arxiv.org/abs/2112.13112
Deep reinforcement learning (RL) has proved to be a competitive heuristic for solving small-sized instances of traveling salesman problems (TSP), but its performance on larger-sized instances is insufficient. Since training on large instances is impr
Externí odkaz:
http://arxiv.org/abs/2110.03595
Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger instances. In
Externí odkaz:
http://arxiv.org/abs/2110.02843