遠くへ行くには共に行け:多様な選好が報酬最適化のカリキュラムを生む
To Go Far, Go Together: Diverse Preferences Induce a Curriculum for Reward Optimization
人間のフィードバックから報酬モデルを学習し、ポリシーを最適化する際に、ユーザーごとの報酬モデルの最適化の難しさに着目し、多様なユーザー集団に対して自然にカリキュラムが生じることを利用して、木構造のカリキュラムを自動構築するCurriPOを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Taehyung Kim, Jongeun Choi
分類: cs.LG, cs.RO
原文アブストラクト
Learning a reward model from human feedback and optimizing a policy against it is one approach to aligning AI systems with individual users. From a fairness perspective, existing work improves such alignment by developing data-efficient and accurate reward models that capture minority preferences despite scarce data. We push this line of inquiry one step further and argue that data-efficient and accurate per-user reward models are not sufficient: users whose reward models are difficult to \textit{optimize} at the policy level can become a new underserved group. We start from the observation that one user's reward model can be easy to optimize from the initial policy while another's is not. We argue that, given a sufficiently diverse user population, a curriculum naturally emerges between easy- and hard-to-optimize reward models. Building on this insight, we propose CurriPO, which grows a tree-structured curriculum to accommodate diverse user-specific objectives, covering the population in a single traversal. Specifically, CurriPO automatically constructs a curriculum over diverse user reward models, allowing it to branch from the existing curriculum and reuse reward models previously incorporated into the curriculum. To the best of our knowledge, this is the first work to explicitly exploit multi-user structure to address optimization in AI alignment. Extensive experiments on personalized continuous control in a simulated environment show that CurriPO achieves $1.2$--$2.1\times$ the population satisfaction of the strongest baseline while substantially reducing training time. Additional analysis attributes much of this improvement to the users left underserved by conventional optimization.
関連論文
- 価値の進化的起源:AIアライメント、感覚、実存的リスクへの示唆AIアライメント