OGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action Models

Experiments on LIBERO and MetaWorld show that OGPO consistently improves VLA policy performance over standard supervised fine-tuning. It comes from a paper posted to arXiv on 12 October 2026. Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation over robot demonstrations. While effective for learning feasible actions, this paradigm supervises policies to reproduce expert actions at each step, biasing them toward demonstration-specific action paths and providing limited guidance for recovering toward task-progress states once execution deviates from demonstrated trajectories. To address this limitation, we propose OGPO, an Offline Goal-conditioned Policy Optimization framework for recoverable VLA post-training. Instead of treating offline demonstrations merely as step-wise action labels, OGPO adaptively relabels trajectories with semantic key states and constructs goal-conditioned process rewards to optimize the policy for reaching these task-progress states. In this way, OGPO shifts VLA post-training from trajectory-level action imitation to key-state reachability learning, enabling policies to acquire a more robust ability to complete goal states from feasible off-demonstration states without requiring additional online interaction. Moreover, evaluations on LIBERO-Plus and our proposed LIBERO-ReAct, a mid-execution perturbation benchmark, further demonstrate that OGPO achieves stronger robustness and goal-directed recoverability under distribution shifts and recoverable off-demonstration states.

Why it counts

Experiments on LIBERO and MetaWorld show that OGPO consistently improves VLA policy performance over standard supervised fine-tuning.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.