Search · four archives
Search · four archives
25 papers · ranked by Valyu relevance
Amadeus Maes, Mauricio Barahona, Claudia Clopath
Sequential behaviour is often compositional and organised across multiple time scales: a set of individual elements developing on short time scales (motifs) are combined to form longer functional sequences (syntax). Such organisation leads to a natural hierarchy that can be used advantageously for learning, since the…
Jun‐Young Chung, Sungjin Ahn, Yoshua Bengio
Learning both hierarchical and temporal representation has been among the longstanding challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can…
Andrew P. Levy, George Konidaris, Robert Platt, Kate Saenko
Hierarchical agents have the potential to solve sequential decision making tasks with greater sample efficiency than their non-hierarchical counterparts because hierarchical agents can break down tasks into sets of subtasks that only require short sequences of decisions. In order to realize this potential of faster…
Nicolas Duminy, Sao Mai Nguyen, Dominique Duhaut
We aim at a robot capable to learn sequences of actions to achieve a field of complex tasks. In this paper, we are considering the learning of a set of interrelated complex tasks hierarchically organized. To learn this high-dimensional mapping between a continuous high-dimensional space of tasks and an infinite…
Taesup Kim, Sungjin Ahn, Yoshua Bengio
We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state…
Adam Eichenbaum, Jason M. Scimeca, Mark D’Esposito
Humans can draw insight from previous experiences in order to quickly adapt to novel environments that share a common underlying structure. Here we combine functional imaging and computational modeling to identify the neural systems that support the discovery and transfer of hierarchical task structure. Human subjects…
Tejas Savalia, Anuj Shukla, Raju S. Bapi
The capacity to sequence information is central to human performance. Sequencing ability forms the foundation stone for higher order cognition related to language and goal-directed planning. Information related to the order of items, their timing, chunking and hierarchical organization are important aspects in…
Laxmi R. Iyer, Ali A. Minai
—Learning meaningful sentences is different from learning a random set of words. When humans understand the meaning, the learning occurs relatively quickly. What mechanisms enable this to happen? In this paper, we examine the learning of novel sequences in familiar situations. We embed the Small World of Words…
Daniel Rasmussen, Aaron Voelker, Chris Eliasmith, Gennady Cymbalyuk
We develop a novel, biologically detailed neural model of reinforcement learning (RL) processes in the brain. This model incorporates a broad range of biological features that pose challenges to neural RL, such as temporally extended action sequences, continuous environments involving unknown time delays, and…
Robin Schiewer, Anand Subramoney, Laurenz Wiskott
Hierarchical model-based reinforcement learning (HMBRL) aims to combine the sample efficiency of model-based reinforcement learning with the abstraction capability of hierarchical reinforcement learning. While HMBRL has great potential, the structural and conceptual complexities of current approaches make it…
Tatsuro Yamada, Shingo Murata, Hiroaki Arie, Tetsuya Ogata
To work cooperatively with humans by using language, robots must not only acquire a mapping between language and their behavior but also autonomously utilize the mapping in appropriate contexts of interactive tasks online. To this end, we propose a novel learning method linking language to robot behavior by means of a…
Ofir Nachum, Haoran Tang, Xingyu Lu, Shixiang Gu + 2 more
'Sergey Levine'] Hierarchical reinforcement learning has demonstrated significant success at solving difficult reinforcement learning (RL) tasks. Previous works have motivated the use of hierarchy by appealing to a number of intuitive benefits, including learning over temporally extended transitions, exploring over…
Maria K Eckstein, Anne GE Collins
Humans have the fascinating ability to achieve goals in a complex and constantly changing world, still surpassing modern machine learning algorithms in terms of flexibility and learning speed. It is generally accepted that a crucial factor for this ability is the use of abstract, hierarchical representations, which…
Sven Wientjes, Clay B. Holroyd
Humans have the ability to craft abstract, temporally extended and hierarchically organized plans. For instance, when considering how to make spaghetti for dinner, we typically concern ourselves with useful “subgoals” in the task, such as cutting onions, boiling pasta, and cooking a sauce, rather than particulars such…
Lituan Wang, Yangqin Feng, Qiufang Fu, Jianyong Wang + 4 more
'Xiaolan Fu' 'Lei Zhang' 'Zhang Yi'] Although many studies have provided evidence that abstract knowledge can be acquired in artificial grammar learning, it remains unclear how abstract knowledge can be attained in sequence learning. To address this issue, we proposed a dual simple recurrent network (DSRN) model that…
Liyu Xia, Anne G. E. Collins
Humans use prior knowledge to efficiently solve novel tasks, but how they structure past knowledge to enable such fast generalization is not well understood. We recently proposed that hierarchical state abstraction enabled generalization of simple one-step rules, by inferring context clusters for each rule. However…
Sao Mai Nguyen, Nicolas Duminy, Alexandre Manoury, Dominique Duhaut + 1 more
'Cédric Buche'] Abstract Multi-task learning by robots poses the challenge of the domain knowledge: complexity of tasks, complexity of the actions required, relationship between tasks for transfer learning. We demonstrate that this domain knowledge can be learned to address the challenges in life-long learning.…
Xiaomao Zhou, Tao Bai, Yanbin Gao, Yuntao Han
Extensive studies have shown that many animals’ capability of forming spatial representations for self-localization, path planning, and navigation relies on the functionalities of place and head-direction (HD) cells in the hippocampus. Although there are numerous hippocampal modeling approaches, only a few span the…
Pieter Verbeke, Tom Verguts
The Rescorla-Wagner rule remains the most popular tool to describe human behavior in reinforcement learning tasks. Nevertheless, it cannot fit human learning in complex environments. Previous work proposed several hierarchical extensions of this learning rule. However, it remains unclear when a flat (non-hierarchical)…
Authors not listed
Digital twins are virtual companions for the design, scale-up, and control of chemical processes. Equipping digital twins with mechanistic models of their mirrored unit operation expands their range of applicability compared to pure data-driven models. As constructing mechanistic models requires time, effort, and…
Authors not listed
Multiscale modeling of complex chemical systems—ranging from polymers to biomolecules—requires coarse-grained (CG) techniques to bridge atomic-scale interactions with mesoscopic behavior. Traditional CG methods rely on handcrafted potentials, limiting their transferability across systems. We propose a…
Authors not listed
Accurate prediction of chemical reaction yields remains essential for accelerating synthesis optimization, yet current machine learning models face critical limitations in capturing temporal dynamics, providing calibrated uncertainty estimates, and explicitly modeling reactant-to-product transformations. Here we…
Rebecca Lindsey, Awwal Oladipupo, Sorin Bastea, Bradley Steele + 2 more
Machine-learned interatomic models have growing in popularity due to their ability to afford near quantum-accurate predictions for complex phenomena, with orders-of-magnitude greater computational efficiency. However, these models struggle when applied to systems of many element types due to the near exponential…
Fuzhan Rahmanian, Robert M. Lee, Dominik Linzner, Kathrin Michel + 4 more
Predicting and monitoring battery life early and across chemistries is a significant challenge due to the plethora of degradation paths, form factors, and electrochemical testing protocols. Existing models typically translate poorly across different electrode, electrolyte, and additive materials, mostly require a fixed…
Chenxi Sui, Ziyang Jiang, Genesis Higueros, David Carlson + 1 more
High-performance batteries are poised for electrification of vehicles and therefore mitigate greenhouse gas emissions, which, in turn, promote a sustainable future. However, the design of optimized batteries is challenging due to the nonlinear governing physics and electrochemistry. Recent advancements have…