Principled Fast And Meta Knowledge Learners For Continual Reinforcement Learning

Abstract

Inspired by the human learning and memory system, particularly the interplay between the hippocampus and cerebral cortex, this study proposes a dual-learner framework comprising a fast learner and a meta learner to address continual Reinforcement Learning~(RL) problems. These two learners are coupled to perform distinct yet complementary roles: the fast learner focuses on knowledge transfer, while the meta learner ensures knowledge integration. In contrast to traditional multi-task RL approaches that share knowledge through average return maximization, our meta learner incrementally integrates new experiences by explicitly minimizing catastrophic forgetting, thereby supporting efficient cumulative knowledge transfer for the fast learner. To facilitate rapid adaptation in new environments, we introduce an adaptive meta warm-up mechanism that selectively harnesses past knowledge. We conduct experiments in various pixel-based and continuous control benchmarks, revealing the superior perfo

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysun2026principled

Related papers

• Learning To Reinforcement Learn (2016)0.00
• Efficient Meta Reinforcement Learning For Preference-based Fast Adaptation (2022)0.00
• Deep Online Learning Via Meta-learning: Continual Adaptation For Model-based RL (2018)0.00
• Continual Knowledge Adaptation For Reinforcement Learning (2025)0.00
• HMRL: Hyper-meta Learning For Sparse Reward Reinforcement Learning Problem (2020)0.00
• RL\(^3\): Boosting Meta Reinforcement Learning Via RL Inside RL\(^2\) (2023)0.00
• Context Meta-reinforcement Learning Via Neuromodulation (2021)6.34
• On The Effectiveness Of Fine-tuning Versus Meta-reinforcement Learning (2022)0.00