English
Related papers

Related papers: Adaptive Rational Activations to Boost Deep Reinfo…

200 papers

Reinforcement learning has traditionally focused on a singular objective: learning policies that select actions to maximize reward. We challenge this paradigm by asking: what if we explicitly architected RL systems as inference engines that…

Artificial Intelligence · Computer Science 2025-11-13 Mehrdad Zakershahrak

Reinforcement learning has exceeded human-level performance in game playing AI with deep learning methods according to the experiments from DeepMind on Go and Atari games. Deep learning solves high dimension input problems which stop the…

Machine Learning · Computer Science 2019-09-12 Yue Zheng

In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A…

Being able to reason in an environment with a large number of discrete actions is essential to bringing reinforcement learning to a larger class of problems. Recommender systems, industrial plants and language models are only some of the…

Most learning algorithms are not invariant to the scale of the function that is being approximated. We propose to adaptively normalize the targets used in learning. This is useful in value-based reinforcement learning, where the magnitude…

Machine Learning · Computer Science 2016-08-17 Hado van Hasselt , Arthur Guez , Matteo Hessel , Volodymyr Mnih , David Silver

State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks…

Machine Learning · Computer Science 2022-11-17 Ofir Moshe , Gil Fidel , Ron Bitton , Asaf Shabtai

Deep learning models are often not easily adaptable to new tasks and require task-specific adjustments. The differentiable neural computer (DNC), a memory-augmented neural network, is designed as a general problem solver which can be used…

Computation and Language · Computer Science 2018-07-10 Jörg Franke , Jan Niehues , Alex Waibel

Because of the pervasive use of deep neural networks (DNNs), especially in high-stakes domains, the interpretability of DNNs has received increased attention. The general idea of rationale extraction (RE) is to provide an…

Machine Learning · Computer Science 2026-05-29 Jiayi Dai , Randy Goebel

The emergence of powerful artificial intelligence is defining new research directions in neuroscience. To date, this research has focused largely on deep neural networks trained using supervised learning, in tasks such as image…

Artificial Intelligence · Computer Science 2020-07-09 Matthew Botvinick , Jane X. Wang , Will Dabney , Kevin J. Miller , Zeb Kurth-Nelson

Real-world reinforcement learning tasks often involve some form of partial observability where the observations only give a partial or noisy view of the true state of the world. Such tasks typically require some form of memory, where the…

Machine Learning · Computer Science 2022-11-11 Kevin Esslinger , Robert Platt , Christopher Amato

In this review, we describe the singular success of attractor neural network models in describing how the brain maintains persistent activity states for working memory, error-corrects, and integrates noisy cues. We consider the mechanisms…

Neurons and Cognition · Quantitative Biology 2022-03-03 Mikail Khona , Ila R. Fiete

Neural algorithmic reasoning is an emerging area of machine learning that focuses on building neural networks capable of solving complex algorithmic tasks. Recent advancements predominantly follow the standard supervised learning paradigm…

Machine Learning · Computer Science 2025-01-03 Hefei Li , Chao Peng , Chenyang Xu , Zhengfeng Yang

Neural networks, as currently designed, fall short of achieving true logical intelligence. Modern AI models rely on standard neural computation-inner-product-based transformations and nonlinear activations-to approximate patterns from data.…

Artificial Intelligence · Computer Science 2025-02-05 Youngsung Kim

Reinforcement learning (RL) is a powerful technique for training intelligent agents, but understanding why these agents make specific decisions can be quite challenging. This lack of transparency in RL models has been a long-standing…

Machine Learning · Computer Science 2024-04-02 Wenhao Lu , Xufeng Zhao , Thilo Fryen , Jae Hee Lee , Mengdi Li , Sven Magg , Stefan Wermter

The remarkable capabilities of modern large reasoning models are largely unlocked through post-training techniques such as supervised fine-tuning (SFT) and reinforcement learning (RL). However, the architectural mechanisms behind such…

Artificial Intelligence · Computer Science 2026-04-15 Yein Park , Minbyul Jeong , Jaewoo Kang

Deep neural networks give us a powerful method to model the training dataset's relationship between input and output. We can regard that as a complex adaptive system consisting of many artificial neurons that work as an adaptive memory as a…

Disordered Systems and Neural Networks · Physics 2024-05-08 Kenichi Nakazato

We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechanism in the framework…

Machine Learning · Computer Science 2018-07-05 Tsendsuren Munkhdalai , Xingdi Yuan , Soroush Mehri , Adam Trischler

We propose Neural Reasoner, a framework for neural network-based reasoning over natural language sentences. Given a question, Neural Reasoner can infer over multiple supporting facts and find an answer to the question in specific forms.…

Artificial Intelligence · Computer Science 2015-08-25 Baolin Peng , Zhengdong Lu , Hang Li , Kam-Fai Wong

Large Language Models (LLMs) have demonstrated impressive real-world utility, exemplifying artificial useful intelligence (AUI). However, their ability to reason adaptively and robustly -- the hallmarks of artificial general intelligence…

Machine Learning · Computer Science 2025-08-27 Seungwook Han , Jyothish Pari , Samuel J. Gershman , Pulkit Agrawal

Active learning identifies data points to label that are expected to be the most useful in improving a supervised model. Opportunistic active learning incorporates active learning into interactive tasks that constrain possible queries…

Computation and Language · Computer Science 2018-08-31 Aishwarya Padmakumar , Peter Stone , Raymond J. Mooney