Query optimizers are a performance-critical component in every database
...
Safe exploration is critical for using reinforcement learning (RL) in
ri...
First-order methods for quadratic optimization such as OSQP are widely u...
Corrective interventions while a robot is learning to automate a task pr...
Cognitive control, the ability of a system to adapt to the demands of a ...
Researchers and practitioners in the field of reinforcement learning (RL...
Safety remains a central obstacle preventing widespread use of RL in the...
The practical usage of reinforcement learning agents is often bottleneck...