Multi-CALF: 統計的保証付き政策結合アプローチ
Multi-CALF: A Policy Combination Approach with Statistical Guarantees
強化学習政策を相対的価値改善に基づいて組み合わせるMulti-CALFを提案し、安定性保証を継承しつつ性能向上を実現、収束確率や偏差・収束時間の理論的保証を与えた。
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: Georgiy Malaniya, Anton Bolychev, Grigory Yaremenko, Anastasia Krasnaya, Pavel Osinenko
分類: cs.LG, cs.AI, cs.RO, cs.SY, eess.SY, math.OC
原文アブストラクト
We introduce Multi-CALF, an algorithm that intelligently combines reinforcement learning policies based on their relative value improvements. Our approach integrates a standard RL policy with a theoretically-backed alternative policy, inheriting formal stability guarantees while often achieving better performance than either policy individually. We prove that our combined policy converges to a specified goal set with known probability and provide precise bounds on maximum deviation and convergence time. Empirical validation on control tasks demonstrates enhanced performance while maintaining stability guarantees.
