control policies
Control policies in AI refer to strategies or rules that dictate how an agent interacts with its environment to maximize cumulative reward. This concept is fundamental in reinforcement learning, where learning effective policies is the main goal.
- Convergent Functions, Divergent Forms
- HYPRL: Reinforcement Learning of Control Policies for Hyperproperties
- Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
- RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics
- UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning