OGBench

Researchers have identified that training instability in reinforcement learning with flow-matching policies is caused by the vanilla sampling strategy, not iterative action generation. They introduced…

Researchers introduced Latent Policy Steering (LPS), a new offline reinforcement learning method that directly integrates Q-gradients from the original action space into latent-space optimization, ach…

Researchers have developed CARL (Contrastive Action-based Representations for Reusable Local Control), a new algorithm that exploits local dynamics regularity to learn reusable skills for hierarchical…