統計的レバレッジスコアによる多様性考慮型経験リプレイ
Diversity-Aware Experience Replay via Statistical Leverage Scores
リプレイバッファ内の遷移を統計的レバレッジでスコアリングし、稀な経験を優先的にサンプリングする手法を提案。裾の重い特徴選択や軌跡窓への適用でロボット学習の多様性を向上させる。
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: Shaifalee Saxena, Alexander Scheinker
分類: cs.RO, cs.LG
原文アブストラクト
Off-policy deep reinforcement learning trains on random samples from a replay buffer of past experience. In physical robot settings, that buffer is dominated by routine: thousands of near-identical transitions from normal operation, while the rare events that define the edges of the task are rarely sampled. We propose scoring every stored transition by its statistical leverage, which measures how unusual it is relative to the buffer's own data, computed from the stored numbers alone, with no labels, rewards, or value network. We draw each mini-batch from a mixture of this score and uniform sampling. First, the natural way to build the score along the directions where the data varies most turns out to be blind when actions are stored as one-hot indicators, because indicator columns always win the variance ranking; we instead select the feature columns with the heaviest tails (largest kurtosis) where small far-away populations are revealed. Second, the importance weights that prioritized replay uses to keep gradients unbiased cancel the method exactly: with full correction, training matches uniform sampling, so we drop the correction and deliberately optimize the rebalanced objective. Third, when the rare situations of a log are relational, visible only in how a stretch of behavior relates to its goal, not in any single stored coordinate-per-transition scores are blind; applying the same tail rule to short trajectory windows described relative to their goal restores the signal, and on a three-joint arm that must push an object around an obstacle it raises the rare-task success from 0.49 to 0.69 against a labeled-oracle ceiling of 0.74.
関連論文
- 近傍Mixup経験リプレイ:連続制御タスクのサンプル効率を高める局所的凸補間強化学習/経験リプレイ