CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization
Learned visual reward models are increasingly used to optimize robot policies, yet a reward model can score an execution that acts on the wrong object as highly as one that completes the task. We show that optimizing such a reward can amplify these wrong-object failures while reward and task success both rise, so the s...
Jia-Xuan Luo, Xing-Guo Xu, Shan-Shan Wang et al.
· 0 citations