EMCES: Episodic Memory Guides RL Data Generation

jiqizhixin · x · 2026-07-10

Researchers from Zhejiang Sci-Tech University and Nanjing University introduced the EMCES system, which uses episodic memory to guide diffusion models in generating high-quality synthetic training data for reinforcement learning, prioritizing the most valuable past experiences.

Experiments show that this method outperforms existing approaches across multiple environments, effectively boosting RL algorithm performance. Additionally, the research leveraged hashing tricks to reduce storage space by 8000x and time by 25.5x without any loss in quality.

Original post →

More from Research

Research channel →