כתבה
arXiv cs.AI ·
ALER: כתיבה מתפסקת ללמידה תוך כדי חיזוק
ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning
ALER הוא אלגוריתם חדש ללמידה תוך כדי חיזוק. הוא משלב LSTM עם זיכרון סלוטים. ALER מגיע לשיעור הצלחה גבוה במשימות שונות, כולל Rune-Mazes ו-Endless T-Maze.
תקציר מקורי באנגליתarXiv:2610.00592v1 Announce Type: cross Abstract: In partially observable reinforcement learning (RL), a later observation can make stored information obsolete or change what it implies for the next decision. Memory architectures and benchmarks for RL mostly test retention, the ability to keep information unchanged until it is needed. We formalize two further requirements. Rewriting sets the decision-relevant content to a value independent of the old one, and experience fusion transforms the old content by a rule that a later observation specifies. For tasks built from such updates, we count the memory states that a solution needs, and several baselines reach their lowest success rates on compositions that need more states. We introduce ALER (Adaptive Learnable Experience Rewriting), an ag
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית