Explainability in deep reinforcement learning
A Heuillet, F Couthouis, N Díaz-Rodríguez - Knowledge-Based Systems, 2021 - Elsevier
A large set of the explainable Artificial Intelligence (XAI) literature is emerging on feature
relevance techniques to explain a deep neural network (DNN) output or explaining models …
relevance techniques to explain a deep neural network (DNN) output or explaining models …
Modular deep learning
Transfer learning has recently become the dominant paradigm of machine learning. Pre-
trained models fine-tuned for downstream tasks achieve better performance with fewer …
trained models fine-tuned for downstream tasks achieve better performance with fewer …
How to reuse and compose knowledge for a lifetime of tasks: A survey on continual learning and functional composition
A major goal of artificial intelligence (AI) is to create an agent capable of acquiring a general
understanding of the world. Such an agent would require the ability to continually …
understanding of the world. Such an agent would require the ability to continually …
Deep reinforcement learning for transportation network combinatorial optimization: A survey
Q Wang, C Tang - Knowledge-Based Systems, 2021 - Elsevier
Traveling salesman and vehicle routing problems with their variants, as classic
combinatorial optimization problems, have attracted considerable attention for decades of …
combinatorial optimization problems, have attracted considerable attention for decades of …
Compositional generalization via neural-symbolic stack machines
Despite achieving tremendous success, existing deep learning models have exposed
limitations in compositional generalization, the capability to learn compositional rules and …
limitations in compositional generalization, the capability to learn compositional rules and …
Evolving reinforcement learning algorithms
We propose a method for meta-learning reinforcement learning algorithms by searching
over the space of computational graphs which compute the loss function for a value-based …
over the space of computational graphs which compute the loss function for a value-based …
Neuro-symbolic visual reasoning: Disentangling
Visual reasoning tasks such as visual question answering (VQA) require an interplay of
visual perception with reasoning about the question semantics grounded in perception …
visual perception with reasoning about the question semantics grounded in perception …
Learning to solve combinatorial optimization problems on real-world graphs in linear time
I Drori, A Kharkar, WR Sickinger, B Kates… - 2020 19th IEEE …, 2020 - ieeexplore.ieee.org
Combinatorial optimization algorithms for graph problems are usually designed afresh for
each new problem with careful attention by an expert to the problem structure. In this work …
each new problem with careful attention by an expert to the problem structure. In this work …
[HTML][HTML] Reinforcement Learning in Manufacturing Control: Baselines, challenges and ways forward
Abstract The field of Neural Combinatorial Optimization (NCO) offers multiple learning-
based approaches to solve well-known combinatorial optimization tasks such as Traveling …
based approaches to solve well-known combinatorial optimization tasks such as Traveling …
Neural relational inference with fast modular meta-learning
Graph neural networks (GNNs) are effective models for many dynamical systems consisting
of entities and relations. Although most GNN applications assume a single type of entity and …
of entities and relations. Although most GNN applications assume a single type of entity and …