Tag: Reinforcement Learning

A new scoping review of 130 studies finds that reinforcement learning for long-horizon robotic manipulation is dominated by hierarchical methods, ...

An open-source simulation framework called T-REX exposes how reinforcement learning traffic signal controllers falter under lane-blocking incidents, revealing that no ...

A new reinforcement learning optimizer called LIGHT uses dynamic graph attention and logarithmic reward shaping to cut query latency on ...

A position paper argues that robots' direct, unmediated coupling with the physical world makes human-centered AI and robotics a distinct ...

A new open access survey reviews AI methods for operating power grids with high penetration of distributed energy resources and ...

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

Researchers trained a reinforcement learning controller entirely on a neural-operator digital twin and deployed it on the MuVacAS vacuum prototype ...

A systematic review of 78 papers examines how machine learning methods support demand forecasting and inventory decision-making.

A new VR and reinforcement learning framework predicts student knowledge mastery with up to 96.8 percent accuracy and adjusts teaching ...

A new reinforcement learning framework called RL-MindFlow combines multimodal emotion perception with a PID-controlled safety mechanism, reporting higher emotion recognition ...

A new study combines whole-word-masked BERT, a bidirectional LSTM and deep reinforcement learning to turn Chinese hotel guest reviews directly ...

An attention-enhanced meta-reinforcement learning scheduler reduced URLLC violations to 63.11% versus 90.54% for DQN and 79.52% for PPO in single-cell ...

A preregistered study of 127 adolescents aged 10 to 20 shows that young people infer latent motives such as greed ...

Researchers propose an LLM-based framework that combines Large Language Models, Knowledge Graphs, and Reinforcement Learning to automate data governance in ...

A new theoretical article proposes that the effectiveness of reinforcement procedures in ABA depends on the fidelity of the reward ...

An offline, uncertainty-aware reinforcement learning scheduler called URSA lifts SLO attainment in LLM inference serving to 90.4 percent across three ...

A modelling study finds that abrupt headway switching during packet loss, not the loss of feedforward information itself, is the ...

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

A hybrid AI system achieved strong skill-level prediction on a public music-learning dataset, but its training recommendations remain to be ...

A simulator study found that semantic terrain labels guided a unified behavior-cloning policy to select flat-ground and stairway behaviors for ...