Complementary Learning Systems

Latest papers

8 papers1 paper in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Permanent and Transient Representations for Continual Reinforcement Learning
Nov 5, 2026Nishanth Anand, Doina PrecupComplementary Learning Systems Continual Learning
School of Computer Science, McGill University and Mila · School of Computer Science, McGill University, Mila, and Google DeepMind
Episodic looking - using reinforcement learning to bias perception enhances few-shot and continual learning with protection from forgetting
Oct 28, 2026David Rawlinson, Gideon KowadloComplementary Learning Systems Continual Learning
Cerenaut Melbourne Australia
Dual-Layer Agentic Memory with Fast Write Routing and Slow Consolidation
Aug 23, 2026Wenzhi Li, Dong Nie, Rui Lan +7Continual Learning for LLM Agents Continual Learning
Zhejiang University · Indepedent Researcher · Xiaohongshu +2
NeuroSynth: A Biologically Inspired Continual Reinforcement Learning Architecture for Mitigating Catastrophic Forgetting
Jul 24, 2026Yash KiniContinual Learning Complementary Learning Systems
James Madison High School Vienna, Virginia, USA
CogniFold: Always-On Proactive Memory via Cognitive Folding
May 13, 2026Suli Wang, Yiqun Duan, Yu Deng +5Cognitive Architectures for AI Agents Continual Learning
1OpenNorve · University of Cambridge · 3NVIDIA +1
Contextual Agentic Memory is a Memo, Not True Memory
Apr 30, 2026Binyan Xu, Xilin Dai, Kehuan ZhangAgent Memory Continual Learning for LLM Agents
The Chinese University of Hong Kong, Hong Kong, China · Zhejiang University, Hangzhou, China
CodaRAG: Connecting the Dots with Associativity Inspired by Complementary Learning
Apr 12, 2026Cheng-Yen Li, Xuanjun Chen, Claire Lin +4Complementary Learning Systems Retrieval-Augmented Generation
National Taiwan University, Taipei, Taiwan · NTU Artificial Intelligence Center of Research Excellence, National Taiwan University.
Active perception and disentangled representations allow continual, episodic zero and few-shot learning
Feb 22, 2026David Rawlinson, Gideon KowadloComplementary Learning Systems Continual Learning
Cerenaut AI Melbourne Australia

Nov 5, 2026J/K move · Enter open · S save

Permanent and Transient Representations for Continual Reinforcement Learning

Nishanth Anand, Doina Precup

School of Computer Science, McGill University and Mila · School of Computer Science, McGill University, Mila, and Google DeepMind

Complementary Learning Systems Continual Learning Continual RL Online Continual Learning Function Approximation in RL Representation Learning for RL

Open paper AskPDF arXiv

Continual Reinforcement Learning (CRL) agents struggle to adapt to new situations while retaining prior knowledge, leading to a stability-plasticity trade-off. One approach to solving this problem is by using complementary learning systems: one for slow, long-term learning and another for quick, transient adaptation. Anand & Precup (2023) instantiated this idea using permanent and transient value functions, but used the same features in both systems. Intuitively, long-term learning should rely more on parametric representations for broad generalization, while transient learning would be best served by non-parametric representations for situation-specific adaptation. In this paper, we explore this idea both theoretically and empirically. By introducing a novel non-parametric approximation for estimating the transient value function in complex tasks, we demonstrate that our method enables online learning and outperforms competitive baselines on image-based tasks and Craftax-Classic, underscoring the effectiveness of our system-level decomposition.