22 papers · ranked by Valyu relevance
Margherita Tecilla, Andrea Guerra, Lorenzo Rocchi, Sara Määttä + 6 more
'Matteo Bologna' 'Maria Herrojo Ruiz' 'Roberta Biundo' 'Angelo Antonini' 'Florinda Ferreri' 'Moussa Antoine Chalah'] In everyday life, goal-oriented motor behaviour relies on the estimation of the rewards/costs associated with alternative actions and on the appropriate selection of movements. Motor decision making is…
Wenbo Zhang, Hengrui Cai
Deep reinforcement learning (RL) has gained widespread adoption in recent years but faces significant challenges, particularly in unknown and complex environments. Among these, high-dimensional action selection stands out as a critical problem. Existing works often require a sophisticated prior design to eliminate…
Eric Peh, Paritosh Parmar, Basura Fernando
We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection (AS) and Effect-Affinity…
Weng, Yueyang, Xiaopeng Zhang, Yongjin Mu + 4 more
— Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multistep action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies. However, the reduced decision frequency restricts the utilization of recent…
Hao Li, Xin Jin
The basal ganglia are known to be essential for action selection. However, the functional role of basal ganglia direct and indirect pathways in action selection remains unresolved. Here by employing cell-type-specific neuronal recording and manipulation in mice trained in a choice task, we demonstrate that multiple…
Dustin Dannenhauer, Matthew Molineaux, Michael W. Floyd, Noah Reifsnyder + 1 more
'Noah Reifsnyder' 'David W. Aha'] Complex, real-world domains may not be fully modeled for an agent, especially if the agent has never operated in the domain before. The agent's ability to effectively plan and act in such a domain is influenced by its knowledge of when it can perform specific actions and the effects of…
Hao Li, Xin Jin, Laura A Bradfield, Kate M Wassum
The basal ganglia are known to be essential for action selection. However, the functional role of basal ganglia direct and indirect pathways in action selection remains unresolved. Here, by employing cell-type-specific neuronal recording and manipulation in mice trained in a choice task, we demonstrate that multiple…
Mukesh Makwana, Fan Zhang, Dietmar Heinke, Joo-Hyun Song + 1 more
'Adrian M. Haith'] Everyday perception-action interaction often requires selection of a single goal from multiple possibilities. According to a recent framework of attentional control, object selection is guided not only by the well-established factors of perceptual salience and current goals but also by selection…
Jingyao Li, Pengguang Chen, Sitong Wu, Chuanyang Zheng + 2 more
Large Language Models Authors: ['Jingyao Li' 'Pengguang Chen' 'Sitong Wu' 'Chuanyang Zheng' 'Xu Hong' 'Jiaya Jia'] The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this…
S. Zhong, J. Choi, N. Hashoush, D. Babayan + 3 more
Surviving in an uncertain environment requires not only the ability to select the best action, but also the flexibility to withhold inappropriate actions when the environmental conditions change. Although selecting and withholding actions have been extensively studied in both human and animals, there is still lack of…
Sanghyun Yi, John P. O’Doherty
When encountering a novel situation, an intelligent agent needs to find out which actions are most beneficial for interacting with that environment. One purported mechanism for narrowing down the scope of possible actions is the concept of action affordance. Here, we delve into the neuro-computational mechanisms…
Nitin Anisetty, Rohit Manchanda
An ensemble of direct and indirect pathway medium spiny neurons (dMSN and iMSN), compete via their neural activity to drive the decision to approach or avoid an object, respectively. Dopamine acting as a reward prediction error (RPE) signal causes experience-dependent synaptic changes in dMSN and iMSN, thereby shifting…
Masafumi Nejime, Mengxi Yun, Yawei Wang, Takashi Kawai + 5 more
Making appropriate decisions relies on the brain’s capacity to evaluate the expected outcomes of available options and select the most rewarding action. The ventral striatum and midbrain dopamine neurons have been implicated in the option valuation process, consistent with the brain’s reinforcement learning theory in…
Shan Zhong, Nader Pouratian, Paul Schrater, Vassilios Christopoulos
Action selection in cluttered environments, where individuals must simultaneously pursue goals and avoid obstacles, presents a significant challenge for the brain. To understand the underlying mechanisms of action selection in such contexts, we propose a computational model that extends stochastic optimal control…
Andrei Nica, Khimya Khetarpal, Doina Precup
Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the…
Elena Zamaraeva, Christopher M. Collins, Dmytro Antypov, Vladimir V. Gusev + 6 more
Crystal Structure Prediction (CSP) is a fundamental computational problem in materials science. Basin-hopping is a prominent CSP method that combines global Monte Carlo sampling to search over candidate trial structures with local energy minimisation of these candidates. The sampling uses a stochastic policy to…
Mobina Shahbandeh, Parsa Alian, Noor Nashid, Ali Mesbah
End-to-end web testing is challenging due to the need to explore diverse web application functionalities. Current state-of-the-art methods, such as WebCanvas, are not designed for broad functionality exploration; they rely on specific, detailed task descriptions, limiting their adaptability in dynamic web environments.…
Katrina R. Quinn, Florian Sandhaeger, Nima Noury, Ema Žeželić + 1 more
Perceptual decisions have long been framed in terms of the actions used to report a choice. Accordingly, studies of perceptual decision-making have historically relied on tasks with fixed choice-response mappings, in which choice and motor response are inextricably linked. Although several studies have since…
Authors not listed
The identification of kinetically feasible reaction pathways that connect a reactant to its product, including numerous intermediates and transition states, is crucial for predicting chemical reactions and elucidating reaction mechanisms. However, as molecular systems become increasingly complex or larger, the number…
Mark A. Thornton, Diana I. Tamir
Human behavior depends on both internal and external factors. Internally, people’s mental states motivate and govern their behavior. Externally, one’s situation constrains which actions are appropriate or possible. To predict others’ behavior, one must understand the influences of mental states and situations on…
Authors not listed
Computer-aided synthesis planning aims to identify viable synthetic routes from a target compound to readily available building blocks by iteratively decomposing molecules into smaller precursors. Self-play search algorithms, trained with simulated experience, reach state-of-the-art performance. However, these methods…
Authors not listed
While virtual libraries of synthetically accessible compounds have exploded in size to many billions, our capacity to extract valuable drug leads from these vast databases remains limited by computational resources. To overcome this, we developed SLICE SMARTS and Logic In ChEmistry), a powerful new tool designed for…