mlsanityData to 7 Oct 2026

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

arXiv 2608.17347 ↗First posted 18 Aug 2026cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 38 references that are in the map. First posted on arXiv 18 Aug 2026.

Builds on

14 of 38 references.

References · 14

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  3. 2015Prioritized Experience Replaycited by 1,070
  4. 2018DeepMind Control Suitecited by 935
  5. 2017Deep Reinforcement Learning that Matterscited by 727
  6. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  7. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  8. 2018Self-Imitation Learningcited by 135
  9. 2021Generalizable Episodic Memory for Deep Reinforcement Learningcited by 22
  10. 2020Episodic Self-Imitation Learning with Hindsightcited by 10
  11. 2022Towards Improving Exploration in Self-Imitation Learning using Intrinsic Motivationcited by 3
  12. 2024Image-Based Deep Reinforcement Learning with Intrinsically Motivated Stimuli: On the Execution of Complex Robotic Taskscited by 3
2 more
  1. 2022Accelerating Self-Imitation Learning from Demonstrations via Policy Constraints and Q-Ensemblecited by 1
  2. 2025Goal-based Self-Adaptive Generative Adversarial Imitation Learning (Goal-SAGAIL) for Multi-goal Robotic Manipulation Taskscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Passive Reuse to Active Reasoning: Grounding Large Language Models for Neuro-Symbolic Experience Replay
  2. 2026Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
  3. 2025Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
  4. 2026World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays
  5. 2026ARROW: Augmented Replay for RObust World models
  6. 2025Memento 2: Learning by Stateful Reflective Memory
  7. 2018Experience Replay for Continual Learning
  8. 2024Augmenting Replay in World Models for Continual Reinforcement Learning