Metraipolis › archive › dc_0be264893ca3

ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning — arXiv:2610.00592

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.00592
License (as archived)
CC0-1.0
Archived
2026-10-06T12:10:17.110Z
SHA-256 of the archived text
43966b6f2644a817e5f27cfc08e68ce2b5f7c6e9616542c4e04d7c8945686563
Stable URL of this page
https://metraipolis.com/documento/dc_0be264893ca3

How to cite

ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning — arXiv:2610.00592 — arXiv (en), https://arxiv.org/abs/2610.00592 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0be264893ca3 (Metraipolis archive dc_0be264893ca3, sha256 43966b6f2644a817e5f27cfc08e68ce2b5f7c6e9616542c4e04d7c8945686563)
BibTeX
@misc{dc0be264893ca3,
  title = {ALER: Adaptive Learnable Experience Rewriting for Reinforcement Learning — arXiv:2610.00592},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.00592},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0be264893ca3; sha256 43966b6f2644a817e5f27cfc08e68ce2b5f7c6e9616542c4e04d7c8945686563},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.00592. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 agent that pairs an LSTM with a slot memory. An independently addressed Gumbel-Softmax write that concentrates its weight on one slot overwrites that slot, and a learned gate fuses the retrieved content with the recurrent state before the policy and value heads. We also introduce Rune-Mazes, three environments in which rune observations invert, cancel, reset, or repeat updates of a hidden cue under vector and pixel observations. Against seven baselines, ALER reaches a success rate of at least $0.82$ in all sixteen Endless T-Maze configurations and at least $0.99$ on all five Rune T-Maze compositions, and it has the highest mean success rate on four-branch Rune Multi-Corridor with an Invert rune. On pixel-based Rune MiniGrid Memory, it has a higher mean success rate than PPO-LSTM in eight of ten configurations. Project page: this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.00592 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T10:21:28.089Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).