Tag: Soft Actor–Critic

Researchers developed a compressed reinforcement learning controller deployed on a microcontroller that maintained an 83 percent time-in-range in simulated type ...

A deep reinforcement learning framework utilizing high-fidelity digital twins optimizes cooling costs and maintains thermal stability in two Danish data ...

In a simulated wire harness handling study, end-to-end reinforcement learning attained a 98 percent success rate, substantially outperforming multi-agent path ...

A hierarchical attention-based reinforcement learning framework improved slice admission rates by up to 20 percent and cut resource overhead by ...

Researchers report a simulation-based explainability framework that pairs a physics-guided reinforcement learning controller with XGBoost and SHAP analysis to trace ...

The MARLIN framework learns delay prediction and routing from five raw IoT sensor streams, but its benchmark uses synthetic labels ...

A new open-access study reports that a multi-agent reinforcement learning framework combined with bio-inspired hyperparameter optimization outperformed comparison models on ...

A 2026 study linked multimodal emotion decoding to low-latency reinforcement-learning control, improving immersion scores in simulation and yielding preliminary behavioural ...

A new reinforcement learning method called FA-PPO was the only tested algorithm to complete simulated UAV obstacle-avoidance tasks across three ...

A simulation-only manufacturing controller reduced emissions by 24.0% versus a benchmark while achieving mean resilience of 0.875, but exceeded the ...