Tag: offline reinforcement learning

A new narrative review maps how offline reinforcement learning methods behave when robotic manipulation datasets are small, narrow and noisy.

A federated Decision Transformer reached 92.5% scheduling accuracy in a simulated industrial environment while reducing parameter transmission by 63% relative ...

Researchers at the University of Ottawa have developed a dual-agent reinforcement learning framework that values soccer actions by modeling both ...

A new deep reinforcement learning framework improves personalized e-commerce marketing by balancing short-term conversions with long-term customer value.

Researchers at Hanyang University have developed TACCO, a contrastive learning method that explicitly identifies and suppresses out-of-distribution actions to stabilize ...

Researchers in Shanghai have built a privacy-preserving federated AI system that fuses bedside ventilator, ultrasound, and blood gas data with ...

A new framework called BootDiffLights uses a conditional diffusion model to generate reward signals for decentralized traffic signal control, outperforming ...

A comprehensive review in Artificial Intelligence Review argues that reinforcement learning can overcome the static limitations of traditional recommender systems, ...

Researchers have developed an offline-to-online reinforcement learning framework that uses adversarial action perturbations and an adaptive curriculum to make robot ...

Offline reinforcement learning has long promised a way to build capable artificial agents without allowing them to experiment freely in ...