Relating Human Error–Based Learning to Modern Deep RL Algorithms
Sign Up to like & getrecommendations! Published in 2024 at "Neural Computation"
DOI: 10.1162/neco_a_01721
Abstract: Abstract In human error–based learning, the size and direction of a scalar error (i.e., the “directed error”) are used to update future actions. Modern deep reinforcement learning (RL) methods perform a similar operation but in… read more here.
Keywords: modern deep; human error; error based; deep algorithms ... See more keywords