Neural networks : the official journal of the International Neural Network Society
38692188
Reinforcement Learning (RL) is a significant machine learning subfield that emphasizes learning actions based on environment to obtain optimal behavior policy. RL agents can make decisions at variable time scales in the form of temporal abstractions,...
Neural networks : the official journal of the International Neural Network Society
38762941
Homeostasis is a self-regulatory process, wherein an organism maintains a specific internal physiological state. Homeostatic reinforcement learning (RL) is a framework recently proposed in computational neuroscience to explain animal behavior. Homeos...
Adults struggle to learn non-native speech categories in many experimental settings (Goto, Neuropsychologia, 9(3), 317-323 1971), but learn efficiently in a video game paradigm where non-native speech sounds have functional significance (Lim & Holt, ...
Neural networks : the official journal of the International Neural Network Society
39321563
State representations considerably accelerate learning speed and improve data efficiency for deep reinforcement learning (DRL), especially for visual tasks. Task-relevant state representations could focus on features relevant to the task, filter out ...
Neural networks : the official journal of the International Neural Network Society
39488112
Goal-conditioned reinforcement learning is widely used in robot control, manipulating the robot to accomplish specific tasks by maximizing accumulated rewards. However, the useful reward signal is only received when the desired goal is reached, leadi...
Neural networks : the official journal of the International Neural Network Society
39515081
Designing reward functions that fully align with human intent is often challenging. Preference-based Reinforcement Learning (PbRL) provides a framework where humans can select preferred segments through pairwise comparisons of behavior trajectory seg...
Neural networks : the official journal of the International Neural Network Society
39705770
In this paper we present three neurocontrol problems where the analytic policy gradient via back-propagation through time is used to train a simulated agent to maximise a polynomial reward function in a simulated environment. If the environment inclu...
The Dark Triad (DT), encompassing narcissism, Machiavellianism and psychopathy traits, poses significant societal challenges. Understanding the neural underpinnings of these traits is crucial for developing effective interventions and preventive stra...
Neural networks : the official journal of the International Neural Network Society
39778295
In the domain of online reinforcement learning, strategies that leverage inherent rewards for exploration tend to achieve commendable outcomes within contexts characterized by deceptive or sparse rewards. Counting through the visitation of states is ...
Neural networks : the official journal of the International Neural Network Society
39965524
Navigating multi-agent reinforcement learning (MARL) environments with sparse rewards is notoriously difficult, particularly in suboptimal settings where exploration can be prematurely halted. To tackle these challenges, we introduce Hierarchical Sym...