3 papers
cs.LG2026
WINFlowNets: Warm-up Integrated Networks Training of Generative Flow Networks for Robotics and Machine Fault Adaptation
Zahin Sufiyan, Shadan Golestan, Yoshihiro Mitsuka +2
Generative Flow Networks for continuous scenarios (CFlowNets) have shown promise in solving sequential decision-making tasks by learning stochastic policies using a flow and a retr…
cs.RO2026
ViSA: Visited-State Augmentation for Generalized Goal-Space Contrastive Reinforcement Learning
Issa Nakamura, Tomoya Yamanokuchi, Yuki Kadokawa +5
Goal-Conditioned Reinforcement Learning (GCRL) is a framework for learning a policy that can reach arbitrarily given goals. In particular, Contrastive Reinforcement Learning (CRL)…
cs.RO2025
A Study of the Efficacy of Generative Flow Networks for Robotics and Machine Fault-Adaptation
Zahin Sufiyan, Shadan Golestan, Shotaro Miwa +2
Advancements in robotics have opened possibilities to automate tasks in various fields such as manufacturing, emergency response and healthcare. However, a significant challenge th…