Research map / Continual learning / Online and replay-based

From Anti-Forgetting to Fast Adaptation: Continual Reinforcement Learning with World Models

NeurIPS 2026 · Continual learning › Online and replay-based · approach: Plasticity-preserving continual reinforcement learning

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes continual reinforcement learning with world models to address catastrophic forgetting and enable fast adaptation to sequential tasks, using planning-based decision making instead of model-free CRL methods.

Problem

Continual reinforcement learning requires agents to adapt to sequentially arriving tasks while retaining performance on previous tasks, where existing methods mostly rely on model-free frameworks prone to catastrophic forgetting.

Approach

Uses world models, which accumulate transferable dynamics knowledge and support planning-based decisions, as an alternative to model-free regularization, parameter isolation, or experience replay for continual RL.

Closest papers by meaning

• Continual Reinforcement Learning by Planning with Online World Models (ICML 2025 · similarity 0.91)
• Knowledge Retention in Continual Model-Based Reinforcement Learning (ICML 2025 · similarity 0.89)
• Continual Knowledge Adaptation for Reinforcement Learning (NeurIPS 2025 · similarity 0.88)
• Experience Replay for Continual Learning (NeurIPS 2019 · similarity 0.88)
• A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control (ICML 2025 · similarity 0.87)
• From Static Policies to Adaptive Priors in Offline Reinforcement Learning (NeurIPS 2026 · similarity 0.87)