reward learning

The issue of traffic congestion poses a significant obstacle to the development of global cities. One promising solution to tackle this problem is intelligent traffic signal control (TSC). Recently, TSC strategies leveraging reinforcement learning (RL) have garnered attention among researchers. However, the evaluation of these models has primarily relied on fixed metrics like reward and queue length. This limited evaluation approach provides only a narrow view of the model's decision-making process, impeding its practical implementation...

Previous exposure to drugs of abuse produces impairments in studies of reversal learning, delay discounting and response inhibition tasks. While these studies contribute to the understanding of normal decision-making and how it is impaired by drugs of abuse, they do not fully capture how decision-making impacts the ability to delay gratification for greater long-term benefit. To address this issue, we used a diminishing returns task to study decision-making in rats that had previously self-administered cocaine...

During robot-assisted therapy, a robot typically needs to be partially or fully controlled by therapists, for instance using a Wizard-of-Oz protocol; this makes therapeutic sessions tedious to conduct, as therapists cannot fully focus on the interaction with the person under therapy. In this work, we develop a learning-based behaviour model that can be used to increase the autonomy of a robot's decision-making process. We investigate reinforcement learning as a model training technique and compare different reward functions that consider a user's engagement and activity performance...

Building an investment portfolio is a problem that numerous researchers have addressed for many years. The key goal has always been to balance risk and reward by optimally allocating assets such as stocks, bonds, and cash. In general, the portfolio management process is based on three steps: planning, execution, and feedback, each of which has its objectives and methods to be employed. Starting from Markowitz's mean-variance portfolio theory, different frameworks have been widely accepted, which considerably renewed how asset allocation is being solved...

Evolutionary theorizing has given rise to the idea that responding to any particular threat may be more mandatory than responding to any particular reward. The present three experiments (total N = 375) sought to provide support for this perspective in an emotion dynamics task in which participants continuously rated their affective state in response to appetitive (reward-related) versus aversive (threat-related) images. Even when equating images for arousal and extremity, several negativity effects (e...

Due to its wide application, deep reinforcement learning (DRL) has been extensively studied in the motion planning community in recent years. However, in the current DRL research, regardless of task completion, the state information of the agent will be reset afterward. This leads to a low sample utilization rate and hinders further explorations of the environment. Moreover, in the initial training stage, the agent has a weak learning ability in general, which affects the training efficiency in complex tasks...

In this article, we investigate the Nash-seeking problem of a set of agents, playing an infinite network aggregative Markov game. In particular, we focus on a noncooperative framework where each agent selfishly aims at maximizing its long-term average reward without having explicit information on the model of the environment dynamics and its own reward function. The main contribution of this article is to develop a continuous multiagent reinforcement learning (MARL) algorithm for the Nash-seeking problem in infinite dynamic games with convergence guarantee...

In recent years, generative machine learning algorithms have been successful in designing innovative drug-like molecules. SMILES is a sequence-like language used in most effective drug design models. Due to data's sequential structure, models such as recurrent neural networks and transformers can design pharmacological compounds with optimized efficacy. Large language models have advanced recently, but their implications on drug design have not yet been explored. Although one study successfully pre-trained a large chemistry model (LCM), its application to specific tasks in drug discovery is unknown...

Deep brain stimulation of the subthalamic nucleus is an effective treatment for the clinical motor symptoms of Parkinson's disease, but may alter the ability to learn contingencies between stimuli, actions and outcomes. We investigated how stimulation of the functional subregions in the subthalamic nucleus (motor and cognitive regions) modulates stimulus-action-outcome learning in Parkinson's disease patients. Twelve Parkinson's disease patients with deep brain stimulation of the subthalamic nucleus completed a probabilistic stimulus-action-outcome task while undergoing ventral and dorsal subthalamic nucleus stimulation (within subjects, order counterbalanced)...

Problematic opioid use that emerges in a subset of individuals may be due to pre-existing disruptions in the biobehavioral mechanisms that regulate drug use. The identity of these mechanisms is not known, but emerging evidence suggests that suboptimal decision-making that is observable prior to drug use may contribute to the pathology of addiction and, notably, serve as a powerful phenotype for interrogating biologically based differences in opiate-taking behaviors. The current study investigated the relationship between decision-making phenotypes and opioid-taking behaviors in male and female Long Evans rats...

Impulsive choices prioritize smaller, more immediate rewards over larger, delayed, or potentially uncertain rewards. Impulsive choices are a critical aspect of substance use disorders and maladaptive decision-making across the lifespan. Here, we sought to understand the neuronal underpinnings of expected reward and risk estimation on a trial-by-trial basis during impulsive choices. To do so, we acquired electrical recordings from the human brain while participants carried out a risky decision-making task designed to measure choice impulsivity...

OBJECTIVES: Remembering past rewarding experiences plays a crucial rule in guiding people's decision-making in the future. However, as people age, they become less accurate in remembering past events and more susceptible to forming false memories. An important question is how the decline of episodic memory and increase of false memory may impact older adults' decision-making performance. METHOD: The current study used a newly developed paradigm in which the Deese-Roediger-McDermott false memory paradigm was combined with a reward learning task to create robust false memories of rewarding experiences...

Neonatal brain inflammation produced by intraperitoneal (i.p.) injection of lipopolysaccharide (LPS) results in long-lasting brain dopaminergic injury and motor disturbances in adult rats. The goal of the present work is to investigate the effect of neonatal systemic LPS exposure (1 or 2 mg/kg, i.p. injection in postnatal day 5, P5, male rats)-induced dopaminergic injury to examine methamphetamine (METH)-induced behavioral sensitization as an indicator of drug addiction. On P70, subjects underwent a treatment schedule of 5 once daily subcutaneous (s...

Supervised machine learning-based medical image computing applications necessitate expert label curation, while unlabelled image data might be relatively abundant. Active learning methods aim to prioritise a subset of available image data for expert annotation, for label-efficient model training. We develop a controller neural network that measures priority of images in a sequence of batches, as in batch-mode active learning, for multi-class segmentation tasks. The controller is optimised by rewarding positive task-specific performance gain, within a Markov decision process (MDP) environment that also optimises the task predictor...

BACKGROUND: The U.S. antibiotic market failure has threatened future innovation and supply. Understanding when and why clinicians underutilize recently approved gram-negative antibiotics might help prioritize the patient in future antibiotic development and potential market entry rewards. OBJECTIVE: To determine use patterns of recently U.S. Food and Drug Administration (FDA)-approved gram-negative antibiotics (ceftazidime-avibactam, ceftolozane-tazobactam, meropenem-vaborbactam, plazomicin, eravacycline, imipenem-relebactam-cilastatin, and cefiderocol) and identify factors associated with their preferential use (over traditional generic agents) in patients with gram-negative infections due to pathogens displaying difficult-to-treat resistance (DTR; that is, resistance to all first-line antibiotics)...

Dopamine (DA) neurons of the substantia nigra (SN) and ventral tegmental area generally respond to aversive stimuli or the absence of expected rewards with transient inhibition of firing rates, which can be recapitulated with activation of the lateral habenula (LHb) and eliminated by lesioning the intermediating rostromedial tegmental nucleus (RMTg). However, a minority of DA neurons respond to aversive stimuli, such as foot shock, with a transient increase in firing rate, an outcome that rarely occurs with LHb stimulation...

BACKGROUND: Early adverse experiences are assumed to affect fundamental processes of reward learning and decision-making. However, computational neuroimaging studies investigating these circuits in the context of adversity are sparse and limited to studies conducted in adolescent samples, leaving the long-term effects unexplored. METHODS: Using data from a longitudinal birth cohort study (n=156, 87 females), we investigated associations between adversities and computational markers of reward learning (i...

Punishment learning is learning of the causal relationship between responses and their adverse or undesirable consequences. Here, we review our translational approach for understanding whether, when, and how individuals differ in what they learn during punishment, and how these differences in learning may drive persistent poor or maladaptive decisions. We show that individual differences in punishment insensitivity can emerge from differences between individuals in what they learn about punishment (instrumental contingency knowledge), rather than differences in aversive valuation, reward valuation, general (impulsivity), or specific (habit) behavioral control...

Reward has been known to render the reward-associated stimulus more salient to block effective attentional orienting in space. However, whether and how reward influences goal-directed attention in time remains unclear. Here, we used a modified attentional cueing paradigm to explore the effect of reward on temporal attention, in which the valid targets were given a low monetary reward and invalid targets were given a high monetary reward. The results showed that the temporal cue validity effect was significantly smaller when the competitive reward structure was employed (Experiment 1), and we ruled out the possibility that the results were due to the practice effect (Experiment 2a) or a reward-promoting effect (Experiment 2b)...

Design of hardware based on biological principles of neuronal computation and plasticity in the brain is a leading approach to realizing energy- and sample-efficient AI and learning machines. An important factor in selection of the hardware building blocks is the identification of candidate materials with physical properties suitable to emulate the large dynamic ranges and varied timescales of neuronal signaling. Previous work has shown that the all-or-none spiking behavior of neurons can be mimicked by threshold switches utilizing material phase transitions...