QF3 trains a flow policy from replayed interaction data.
Filtered critic gradients speed reinforcement learning for flow-based robot policies
QF3 updates flow policies using selectively applied action-value gradients, enabling faster humanoid training and manipulation fine-tuning.
Independent
Chung Min Kim · Brent Yi · David McAllister · Hongsuk Choi · Himanshu Gaurav Singh · Jinkun Cao · +4 more
Research Digest··2 min read
Kim and colleagues introduce QF3, an online, off-policy reinforcement learning algorithm for flow policies, which generate robot actions through an iterative learned transformation.
Why this paper
Independent
In one line
QF3 is the first off-policy flow RL method to train humanoid locomotion from scratch, achieve 10x speedup, and transfer zero-shot to hardware.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§