← Back to Benchmarks
simmediumatarimetric · varies

Attention or memory? Neurointerpretable agents in space and time

Description

In neuroscience, attention has been shown to bidirectionally interact with reinforcement learning (RL) processes. This interaction is thought to support dimensionality reduction of task representations, restricting computations to relevant features. However, it remains unclear whether these properties can translate into real algorithmic advantages for artificial agents, especially in dynamic environments. We design a model incorporating a self-attention mechanism that implements task-state repre

Source

http://arxiv.org/abs/2007.04862v2