Problem
Research questions and friction points this paper is trying to address.
Reinforcement Learning
Sample Efficiency
Instant Episode Repetition
Repetition as Reinforcement: Enhancing Sample Efficiency via Instant Episode Repetition in Reinforcement Learning
🤖 AI Summary
研究通过即时重复成功经历的动作序列（IER）来提高强化学习中的样本效率，该方法在多个连续控制任务中优于传统方法。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Reinforcement Learning
Sample Efficiency
Instant Episode Repetition
Action Sequence
🔎 Similar Papers
No similar papers found.
