Density-Aware Reward Aggregation is proposed, an inverse-square-root density correction that gives greater weight to signals from less frequently active rewards that is derived from an inverse-square-root density correction that gives greater weight to signals from less frequently active rewards.
Tong Zheng, Skylar Zhai, Zhan Cheng et al.· 1 citation
Interpretability methods such as probes, activation patches and learned editors are designed to reveal or modify a model's current computation. World models pose a harder requirement: because their predictions become inputs to later predictions, a useful internal correction must survive after editing stops. We therefor...
Jun-Chi Yao, Zi-Yi Wang, You-Ling Huang et al.· 0 citations
Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-stage policies often fail to solve sampled tasks, leaving little useful reward signal for learning. To mitigate this problem, we use on-policy distillation (OPD) to provid...
You-Ling Huang, Tian-Kuo Xu, Jia-Ji Liu et al.· 0 citations
Experiments show that BehR-based training improves long-term alignment in several settings, with the clearest gains in WebShop and less movement in near-ceiling regimes, while preserving or improving single-step prediction quality in three of four settings.
Youling Huang, Guan-Qiao Chen, Junchi Yao et al.· arXiv.org· 4 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.