Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning
Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz +3
In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual…
cs.LG2024
Kolmogorov-Arnold Network for Online Reinforcement Learning
Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz +3
Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer…