Reinforcement learning for large language model post-training often reuses each batch of sampled rollouts for several gradient passes to amortize the cost of generation. Under such multi-pass reuse, existing objectives fail in different ways: unclipped updates collapse as the policy drifts away from the sampling policy...
Xunlan Zhou, Yu-Zheng Zhao, Xu-Hong Huang et al.· 0 citations
SMBAR is a continual learning algorithm that prevents catastrophic forgetting during VLA finetuning without requiring access to the demonstrations of any previously learned task, and is cast as a constrained optimization problem and solved with the method of multipliers.
Experiments on locomotion, navigation and manipulation show consistent gains in interaction efficiency, imitation performance, and robustness, indicating that RECON directs real-environment interaction toward recovery regions around the expert distribution that are underexplored by prior methods, and thereby learns a w...
Xuan-Lin Chen, Zi-Yue Wang, Xunlan Zhou et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.