Machine Heart
Jul 2, 2026 · Artificial Intelligence
EMCES: How Episodic Memory Guides Controllable Sample Synthesis to Boost Reinforcement Learning
The paper introduces EMCES, a method that injects episodic memory into controllable diffusion models and uses a hash‑based state representation to generate high‑value synthetic samples, dramatically improving sample efficiency and downstream reinforcement‑learning performance while cutting storage and time costs.
Diffusion ModelsEpisodic MemoryHashing
0 likes · 14 min read
