Tag: adversarial reinforcement learning
Browse our exclusive articles!
FastGrasp: Learning-Based Fast Dexterous Grasping Control
Discover FastGrasp, a learning-based whole-body control method enabling fast, dexterous grasping with mobile manipulators using tactile feedback and reinfo...
PromptEcho: Annotation-Free Rewards for Text-to-Image RL
Discover PromptEcho, an annotation-free reward method using vision-language models to enhance text-to-image reinforcement learning efficiently and effectiv...
Multi-Task Reinforcement Learning for Autonomous Reef Monitoring
Discover how multi-task reinforcement learning enhances autonomous reef monitoring with adaptable, robust control policies for diverse underwater tasks.
SOAR: Enhancing Diffusion Models with Self-Correction
Discover SOAR, a post-training method that boosts diffusion model performance via self-correction, improving alignment and refinement without reward models...
KG-Reasoner: Reinforced Model for Multi-Hop KG Reasoning
Discover KG-Reasoner, a reinforced model using RL for dynamic, end-to-end multi-hop reasoning over knowledge graphs, boosting complex query accuracy.