Metraipolis › archive › dc_31b728130fa7

Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning — arXiv:2608.17347

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.17347
License (as archived)
CC0-1.0
Archived
2026-10-18T14:48:34.790Z
SHA-256 of the archived text
73bdefc78b3859aa3958b34d238f6dabb0a0fbb8d4883105e0215ad5b66e81eb
Stable URL of this page
https://metraipolis.com/documento/dc_31b728130fa7

How to cite

Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning — arXiv:2608.17347 — arXiv (en), https://arxiv.org/abs/2608.17347 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_31b728130fa7 (Metraipolis archive dc_31b728130fa7, sha256 73bdefc78b3859aa3958b34d238f6dabb0a0fbb8d4883105e0215ad5b66e81eb)
BibTeX
@misc{dc31b728130fa7,
  title = {Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning — arXiv:2608.17347},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17347},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_31b728130fa7; sha256 73bdefc78b3859aa3958b34d238f6dabb0a0fbb8d4883105e0215ad5b66e81eb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17347. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Repetition is a fundamental mechanism in human learning, where revisiting successful experiences strengthens memory, consolidates skills, and improves future performance. Motivated by this biological principle, we introduce Instant Episode Repetition (IER), a simple and novel mechanism that improves sample efficiency by immediately repeating action sequences from successful episodes during environment interaction. Unlike conventional approaches such as Experience Replay and Self-Imitation Learning (SIL), which passively reuse past experience during training updates, IER directly influences the data collection process. Upon identifying a high-reward episode, the agent repeats its action sequence for a fixed number of subsequent episodes, reinforcing valuable behaviors through renewed interaction with the environment. We integrate IER into state-of-the-art SAC and TD3 algorithms and evaluate its effectiveness on continuous-control benchmarks, including MuJoCo, the DeepMind Control Suite, and a real-world dynamic object translation task with a robotic manipulator. Experimental results demonstrate that this simple mechanism improves learning performance over standard and self-imitation-based baselines.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.17347 — 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 2026-10-18T14:47:59.394Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).