Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport
Offline reinforcement learning aims to learn a policy solely from fixed datasets, which often contain multimodal action distributions. Flow policies can naturally represent such multimodal behaviors, but learning an efficient one-step flow policy remains challenging: standard value guidance often leads to mode collapse or exploits overestimation bias in out-of-distribution regions. To address…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
