自己修復型リカレントアンサンブルによる分布シフトからのリアルタイム回復
Self-Repairing Recurrent Ensembles for Real-Time Recovery from Distribution Shift
センサドリフトや故障による分布シフトに対し、マスク付きリカレントネットのアンサンブルとカルマン融合で自己教師ラベルを作り、RFLOでオンライン微調整して回復する手法。
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: Julian Lemmel, Pedro D. Wendel Garcia, Taisuke Kobayashi, Radu Grosu
分類: cs.NE, cs.RO, eess.SY
原文アブストラクト
Deploying a pretrained controller exposes it to conditions that are absent from its training data. Sensor drift, outright sensor failure and accumulating measurement noise all induce a distribution shift that can collapse an otherwise competent policy; typically at a point in time where no expert is available to supply corrective labels. We present a method that lets a policy recover from such shifts online and without supervision. Our controller is an ensemble of recurrent networks, each of which observes a randomly masked subset of the observation vector, and whose Gaussian outputs are combined through sequential Kalman fusion so that confident members dominate the consensus action. At deployment, we treat this consensus as a self-supervised label and fine-tune each member towards it, scaling each member's contribution proportional to the complement of its squared Kalman gain. Gradients are computed using RFLO, an efficient and biologically plausible approximation of Real-Time Recurrent Learning, so that a parameter update follows every environment step and the policy reacts to a shift as it unfolds. On a range of simulated continuous control tasks, our approach recovers close to the original performance after a sensor shift, while ensembles that see the full observation are unable to recover. The same framework subsumes fully online interactive imitation learning: when an expert is present, the consensus label is replaced by the expert action and the identical update rule refines the policy during teleoperation.
関連論文
- 動的不確実性下でのロバストな敵対的方策最適化強化学習/ロバスト制御
- オフラインからオンライン強化学習における敵対的ファインチューニングによるロバストなロボット制御強化学習/ロバスト制御
- ARMOR: 物理攻撃下のUAVのための堅牢な強化学習ベース制御強化学習/ロバスト制御