Pinned
Excited to share Flow Matching Policy Gradients: expressive RL policies trained from rewards using flow matching. It’s an easy, drop-in replacement for Gaussian PPO on control tasks.
- A huge team effort! Fully open data, infrastructure and eval for the community to build onIntroducing ABC: open data, training, and infrastructure for robotics. We release the largest teleop dataset to date, and extensively investigate design decisions, pretraining, and post-training techniques. @arthurallshire @Cinnabar233 @adamrasb @redstone_hong @davidrmcall
- We developed a simple, sample-efficient online RL technique for post-training image generation models. We see it as a possible steerable alternative to CFG, driven by any scalar reward, including human preference.
- Brent and Hongsuk improved FPO to control robots with flow/diffusion models in real time!New project! Flow Policy Gradients for Robot Control tldr; a simple online RL recipe for training and fine-tuning flow policies for robots co-led w/ @redstone_hong: hongsukchoi.github.io/fpo-control
