28 papers · ranked by Valyu relevance
Xinkai Zhang, Jingtao Zhan, Yiqun Liu, Qingyao Ai
Trial-and-error is a fundamental strategy for humans to solve complex problems and a necessary capability for Artificial Intelligence (AI) systems operating in real-world environments. Although several trial-and-error AI techniques have recently been proposed, most of them rely on simple heuristics designed by…
Holger Mohr, Katharina Zwosta, Dimitrije Markovic, Sebastian Bitzer + 2 more
Trial-and-error learning is a universal strategy for establishing which actions are beneficial or harmful in new environments. However, learning stimulus-response associations solely via trial-and-error is often suboptimal, as in many settings dependencies among stimuli and responses can be exploited to increase…
C. Shamasundar
The scope of the topic indicated in the title is as vast as one's life. In addition, a large proportion of learning will have happened outside the participation of one's awareness. Among those events that prompted conscious learning, many would have been lost to memory, and some of them would be too private to…
Sofia Fregni, Uta Wolfensteller, Hannes Ruge
We used fMRI to investigate the neural changes and representational dynamics associated with different learning modes during initial learning and subsequent implementation of previously acquired stimulus-response (S-R) associations. We compared instruction-based learning (INS) and trial-and-error learning (TE) via a…
Charlène Truong, Célia Ruffino, Alexandre Crognier, Christos Paizis + 2 more
'Lionel Crognier' 'Charalambos Papaxanthis'] This study investigates the effects of error-based and reinforcement training on the acquisition and long-term retention of free throw accuracy in basketball. Sixty participants were divided into four groups (n = 15 per group): (i) the error-based group (sensory feedback)…
Jing Wang, Eghbal Hosseini, Nicolas Meirhaeghe, Adam Akkad + 1 more
Learning reduces variability but variability can facilitate learning. This paradoxical relationship has made it challenging to tease apart sources of variability that degrade performance from those that improve it. We tackled this question in a context-dependent timing task requiring humans and monkeys to flexibly…
Naser Al-Fawakhiri, Sarosh Kayani, Samuel D. McDougle
When acquiring a motor skill, learners must practice the skill at a difficulty that is challenging but still manageable in order to gradually improve their performance. In other words, during training the learner must experience success as well as failure. Does there exist an optimal proportion of successes and…
Max Townsend, Matthew Warburton, Carlo Campagnoli, Mark Mon-Williams + 2 more
Strategic behaviour in sensorimotor adaptation tasks is typically described as either a gradual error minimisation process or as a process of learning through trial-and-error. The former predicts a gradual monotonic reduction in error, until some asymptote, while the latter predicts behavioural exploration to discover…
Dániel Rivas-Blanco, Tiago Monteiro, Zsófia Virányi, Friederike Range
To survive and reproduce, animals need to behave adaptively by adjusting their behavior to their environment, with learning facilitating some of these processes. Despite the fact that dogs were the subject species for Pavlov’s original studies on learning, relatively little research has been done exploring dogs’ basic…
Olof Leimar, Andrés E Quiñones, Redouan Bshary, Emilie Snell-Rood
Cognitive flexibility can enhance the ability to adjust to changing environments. Here, we use learning simulations to investigate the possible advantages of flexible learning in volatile (changing) environments. We compare two established learning mechanisms, one with constant learning rates and one with rates that…
Yufei He, Juncheng Liu, Yue Liu, Yibo Li + 4 more
A fundamental limitation of current AI agents is their inability to learn complex skills on the fly at test time, often behaving like "clever but clueless interns" in novel environments. This severely limits their practical utility. To systematically measure and drive progress on this challenge, we first introduce the…
Federico Nardi, A. Aldo Faisal, Shlomi Haar
Error-based and reward-based mechanisms of motor learning co-occur in real-world scenarios but are traditionally isolated in laboratory tasks via feedback manipulations. We examined the distinctiveness of these mechanisms by applying lab-based feedback manipulations to a real-world task. Using Embodied Virtual Reality…
Nicolò Cesa‐Bianchi, Tommaso Cesari, Yishay Mansour, Vianney Perchet
We study a setting in which a learner faces a sequence of decision tasks and is required to make good decisions as quickly as possible. Each task n is associated with a pair (Xn, µn), where Xn is a random variable and µn is its (unknown and potentially negative) expectation. The learner can draw arbitrarily many i.i.d.…
Taisei Sugiyama, Nicolas Schweighofer, Jun Izawa
Humans and animals develop learning-to-learn strategies throughout their lives to accelerate learning. One theory suggests that this is achieved by a metacognitive process of controlling and monitoring learning. Although such learning-to-learn is also observed in motor learning, the metacognitive aspect of learning…
Federico Nardi, A. Aldo Faisal, Shlomi Haar
This study examines the distinctiveness of error-based and reward-based mechanisms in motor learning, which are traditionally isolated in laboratory tasks but co-occur in real-world scenarios. Using Embodied Virtual Reality (EVR) of pool billiards - allowing for full proprioception via interaction with the physical…
Katie J. Harrington, Megan L. Lambert
Cognitive flexibility, the capacity to adapt to changing conditions, is often assessed with reversal learning, in which a learned association must be updated after reward contingencies change. Trials-to-criterion (TTC) is a widely applied learning threshold, but it can misrepresent performance; some individuals improve…
Matthias Deliano, Karsten Tabelow, Reinhard König, Jörg Polzehl + 1 more
'Lutz Jaencke'] Estimation of learning curves is ubiquitously based on proportions of correct responses within moving trial windows. Thereby, it is tacitly assumed that learning performance is constant within the moving windows, which, however, is often not the case. In the present study we demonstrate that violations…
Authors not listed
Developing generalizable machine learning models with minimal data remains a central challenge in materials informatics. Effective models can significantly reduce costly computational simulations and time-intensive experimentation by providing reliable predictions of material properties. In this work, we investigate…
Janarthanan Rajendran, Richard A. Lewis, Vivek Veeriah, Honglak Lee + 1 more
'Satinder Singh'] We present a method for learning intrinsic reward functions to drive the learning of an agent during periods of practice in which extrinsic task rewards are not available. During practice, the environment may differ from the one available for training and evaluation with extrinsic rewards. We refer to…
Authors not listed
Large Language Models (LLMs) based on transformer architectures excel at internet-scale tasks. However, real-world scientific scenarios—such as synthetic chemistry laboratories and autonomous experimental setups—typically involve incremental data generation in batches as new chemical reactions are conducted, unlike…
Jamal Esmaily, Rani Moran, Yasser Roudi, Bahador Bahrami
reinforcement learning Authors: ['Jamal Esmaily' 'Rani Moran' 'Yasser Roudi' 'Bahador Bahrami'] Although evidence integration to the boundary model has successfully explained a wide range of behavioral and neural data in decision making under uncertainty, how animals learn and optimize the boundary remains unresolved.…
Jinfeng Lou, Zijie Liang, Pengkun Liu, Yuxin Zhang + 2 more
Decision-making in urban infrastructure management during extreme events relies heavily on human operators, yet current computational support systems often fail to account for non-monotonic human adaptation and latent psychological biases like overconfidence and defensive overcorrection. This study addresses this gap…
Authors not listed
Machine olfaction—the artificial replication of the sense of smell—faces significant challenges due to the absence of large, standardized training datasets. Unlike vision, language, and audio models, which benefit from extensive corpora such as ImageNet, GLUE, and AudioSet, olfaction lacks scaled equivalents and…
Aki Nikolaidis
For many years, researchers in psychology, education, statistics, and machine learning have been developing practical methods to improve learning speed, retention, and generalizability, and this work has been successful. Many of these methods are rooted in common underlying principles that seem to drive learning and…
Sterling Baird, Jason R. Hall, Taylor D. Sparks
Would you rather search for a line inside a cube or a point inside a square? Physics-based simulations and wet-lab experiments often have symmetries (degeneracies) that allow reducing problem dimensionality or search space, but constraining these degeneracies is often unsupported or difficult to implement in many…
Authors not listed
Integrating machine learning (ML) into drug discovery has ushered in a new era of innovation, dramatically enhancing the efficiency and precision of identifying and developing new therapeutics. This review provides a comprehensive analysis of the current applications of machine learning in drug discovery, focusing on…
Long Qian, Xin Lu, Parvez Haris, Jianyong Zhu + 2 more
Clinical trials are crucial for drug development, but they require significant time and financial resources. Additionally, uncertainties may arise during these trials concerning their results due to concerns surrounding effectiveness, safety, or the enrollment of participants. If robust AI (artificial intelligence)…
Niklas Kühl, Marc Goutier, Lucas Baier, Clemens Wolff + 1 more
'Dominik Martin'] The capabilities of supervised machine learning (SML), especially compared to human abilities, are being discussed in scientific research and in the usage of SML. This study provides an answer to how learning performance differs between humans and machines when there is limited training data. We have…