Related papers: Modulating task outcome value to mitigate real-wor…
Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this…
This study investigated the effects of mental fatigue (MF) induced by a 90-min AX-continuous performance test (AX-CPT) on balance control by addressing the issue of the heterogeneity of individuals' responses. Twenty healthy young active…
Recent work in continual learning has highlighted the stability gap -- a temporary performance drop on previously learned tasks when new ones are introduced. This phenomenon reflects a mismatch between rapid adaptation and strong retention…
Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic…
Recent work has shown that dopamine-modulated STDP can solve many of the issues associated with reinforcement learning, such as the distal reward problem. Spiking neural networks provide a useful technique in implementing reinforcement…
The role of specific cognitive processes in deviations from constant discounting in intertemporal choice is not well understood. We evaluated decreased impatience in intertemporal choice tasks independent of discounting rate and…
Task Free online continual learning (TF-CL) is a challenging problem where the model incrementally learns tasks without explicit task information. Although training with entire data from the past, present as well as future is considered as…
There has become of increasing interest in transcranial alternating current stimulation (tACS) since its inception nearly a decade ago. tACS in modulating brain state is an active area of research and has been demonstrated effective in…
The present literature about possible mechanisms behind the effectivity of noninvasive electromagnetic stimulation in major depressive disorder (MDD) is not very rich. Despite extensive research in applications for clinical practice, the…
The commonly used Reinforcement Learning (RL) model, MDPs (Markov Decision Processes), has a basic premise that rewards depend on the current state and action only. However, many real-world tasks are non-Markovian, which has long-term…
Hawkes processes have been shown to be efficient in modeling bursty sequences in a variety of applications, such as finance and social network activity analysis. Traditionally, these models parameterize each process independently and assume…
Objective motor skill assessment plays a critical role in fields such as surgery, where proficiency is vital for certification and patient safety. Existing assessment methods, however, rely heavily on subjective human judgment, which…
Reinforcement learning (RL) has become a promising paradigm for optimizing Retrieval-Augmented Generation (RAG) in complex reasoning tasks. However, traditional outcome-based RL approaches often suffer from reward sparsity and inefficient…
(This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.) To improve the efficiency of deep reinforcement learning (DRL)-based…
Policy gradient methods are an appealing approach in reinforcement learning because they directly optimize the cumulative reward and can straightforwardly be used with nonlinear function approximators such as neural networks. The two main…
The Reward Prediction Error hypothesis proposes that phasic activity in the midbrain dopaminergic system reflects prediction errors needed for learning in reinforcement learning. Besides the well-documented association between dopamine and…
Model predictive control (MPC) is a popular control method that has proved effective for robotics, among other fields. MPC performs re-planning at every time step. Re-planning is done with a limited horizon per computational and real-time…
Large language models (LLMs) often generate self-contradictory outputs, which severely impacts their reliability and hinders their adoption in practical applications. In video-language models (Video-LLMs), this phenomenon recently draws the…
For decades, focal non-invasive neuromodulation of deep brain regions has not been possible because of the steep depth-focality trade-off of conventional non-invasive brain stimulation (NIBS) techniques, such as transcranial magnetic…
Large language models exhibit impressive reasoning capabilities yet frequently generate plausible but incorrect solutions, a phenomenon commonly termed hallucination. This paper investigates the effect of training objective composition on…