Agentic Episodic Control
Xidong Yang, Wenhao Li, Junjie Sheng, Chuyun Shen, Yun Hua, Xiangfeng Wang

TL;DR
The paper introduces Agentic Episodic Control (AEC), a novel RL architecture integrating large language models and structured memory to improve data efficiency and generalization in complex tasks.
Contribution
AEC combines RL with LLMs and structured memory modules to enhance decision-making, semantic understanding, and environmental reasoning in reinforcement learning agents.
Findings
AEC outperforms baselines on BabyAI-Text tasks
Significant improvement in complex and generalization tasks
Up to 76% performance gain on FindObj
Abstract
Reinforcement learning (RL) has driven breakthroughs in AI, from game-play to scientific discovery and AI alignment. However, its broader applicability remains limited by challenges such as low data efficiency and poor generalizability. Recent advances suggest that large language models, with their rich world knowledge and reasoning capabilities, could complement RL by enabling semantic state modeling and task-agnostic planning. In this work, we propose the Agentic Episodic Control (AEC), a novel architecture that integrates RL with LLMs to enhance decision-making. The AEC can leverage a large language model (LLM) to map the observations into language-grounded embeddings, which further can be stored in an episodic memory for rapid retrieval of high-value experiences. Simultaneously, a World-Graph working memory module is utilized to capture structured environmental dynamics in order to…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Control Systems Optimization
