OGPO is a sample-efficient off-policy method for full finetuning of generative control policies that reaches SOTA on robotic manipulation tasks and can recover from poor behavior-cloning initializations without expert data.
Residual off- policy rl for finetuning behavior cloning policies
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.
citing papers explorer
-
OGPO: Sample Efficient Full-Finetuning of Generative Control Policies
OGPO is a sample-efficient off-policy method for full finetuning of generative control policies that reaches SOTA on robotic manipulation tasks and can recover from poor behavior-cloning initializations without expert data.
-
MoRI: Mixture of RL and IL Experts for Long-Horizon Manipulation Tasks
MoRI dynamically mixes RL and IL experts with variance-based switching and IL regularization to reach 97.5% success in four real-world robotic tasks while cutting human intervention by 85.8%.
-
$\pi^{*}_{0.6}$: a VLA That Learns From Experience
RECAP enables a generalist VLA to self-improve via advantage-conditioned RL on mixed real-world data, more than doubling throughput and halving failure rates on hard manipulation tasks.