FAR: Failure-Aware Retry for Test-Time Recovery and Continual Policy Improvement
2026-07-01 • Robotics
RoboticsArtificial IntelligenceMachine Learning
AI summaryⓘ
The authors created a method called Failure-Aware Retry (FAR) to help robots learn from their mistakes during tasks instead of just trying the same thing again. Their approach uses information from failed attempts to guide the robot away from repeating errors and adds small changes in actions to explore better options. They also use successful recoveries to continually improve the robot's behavior. Tests in both simulations and real-world tasks showed that FAR helps robots succeed more often and learn more efficiently.
robot policyfailure recoverypreference learningaction perturbationreinforcement learningsimulationmanipulation taskspolicy improvementexploration-exploitation
Authors
Haoran Hao, Shahram Najam Syed, Jeffrey Ichnowski, Jeff Schneider
Abstract
Robot policies inevitably encounter failures when deployed in real environments. Naive retries often repeat the same mistakes, while many existing recovery methods rely on human intervention. In this paper, we propose Failure-Aware Retry (FAR), a framework that enables robots to learn from previous failures at test time, adapt their behavior accordingly, and eventually complete the task autonomously. FAR combines Failure-Contrastive Preference Adaptation, which constructs preference learning data from failures to steer the policy away from previously unsuccessful behaviors, with lightweight action perturbations during retries to encourage local exploration. We further incorporate successful recovery trajectories into a training loop for continual policy improvement. Experiments in both simulation and real-world manipulation tasks show that FAR substantially improves success rates and robustness, with average gains of 17.6% over the standard diffusion policy in simulation and 11.7% in the real world. In addition, FAR significantly improves data efficiency under both reset and timestep budgets during continual policy improvement by exploiting informative failure cases.