Add to ORKGWe characterise the problem of abstraction in the context of deep reinforcement learning. Various well established approaches to analogical reasoning and associative memory might be brought to bear on this issue, but they present difficulties because of the need for end-to-end differentiability. We re- view developments in AI and machine learning that could facilitate their adoption
International audienceExplainable Artificial Intelligence (XAI), i.e., the development of more trans...
Current deep learning systems are highly specialized to whatever task they are designed to solve. Th...
When applying the learning systems to real-world problems, which have a lot of unknown or uncertain ...
Reinforcement learning (RL) models the learning process of humans, but as exciting advances are made...
Reinforcement learning presents a challenging problem: agents must generalize experiences, efficient...
Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore...
We are interested in the following general question: is it pos- sible to abstract knowledge that is ...
This paper introduces a novel approach for abstraction selection in reinforcement learning problems ...
Abstraction is a higher order cognitive ability that facilitates the production of rules that are in...
Deep reinforcement learning has gathered much attention recently. Impressive results were achieved i...
This paper deals with the possible benefits of Perceptual Learning in Artificial Intelligence. On th...
How do people learn new abstract concepts? The approach taken in this work is to develop a theoretic...
In this paper, we consider the problem of reinforcement learning in spatial tasks. These tasks have ...
Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic ta...
Automatic data abstraction is an important capability for both benchmarking machine intelligence and...
International audienceExplainable Artificial Intelligence (XAI), i.e., the development of more trans...
Current deep learning systems are highly specialized to whatever task they are designed to solve. Th...
When applying the learning systems to real-world problems, which have a lot of unknown or uncertain ...
Reinforcement learning (RL) models the learning process of humans, but as exciting advances are made...
Reinforcement learning presents a challenging problem: agents must generalize experiences, efficient...
Successful reinforcement learning requires large amounts of data, compute, and some luck. We explore...
We are interested in the following general question: is it pos- sible to abstract knowledge that is ...
This paper introduces a novel approach for abstraction selection in reinforcement learning problems ...
Abstraction is a higher order cognitive ability that facilitates the production of rules that are in...
Deep reinforcement learning has gathered much attention recently. Impressive results were achieved i...
This paper deals with the possible benefits of Perceptual Learning in Artificial Intelligence. On th...
How do people learn new abstract concepts? The approach taken in this work is to develop a theoretic...
In this paper, we consider the problem of reinforcement learning in spatial tasks. These tasks have ...
Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic ta...
Automatic data abstraction is an important capability for both benchmarking machine intelligence and...
International audienceExplainable Artificial Intelligence (XAI), i.e., the development of more trans...
Current deep learning systems are highly specialized to whatever task they are designed to solve. Th...
When applying the learning systems to real-world problems, which have a lot of unknown or uncertain ...