Tsn-affinity: Similarity-driven Parameter Reuse For Continual Offline Reinforcement Learning

Abstract

arXiv:2604.25898v1 Announce Type: new Abstract: Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This setting corresponds to domains where new tasks arise over time, but adapting the model in live environment interactions is expensive, risky, or impossible. However, CORL inherits the dual difficulty of offline reinforcement learning and adapting while preventing catastrophic forgetting. Replay-based continual learning approaches remain a strong baseline but incur memory overhead and suffer from a distribution mismatch between replayed samples and newly learned policies. At the same time, architectural continual learning methods have shown strong potential in supervised learning but remain underexplored in CORL. In this work, we propose TSN-Affinity, a novel CORL method based on TinySubNetworks and Decision Transformer. The method enables task-specific parameteri

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzurek2026tsn

Related papers

• Solving Continual Offline Reinforcement Learning With Decision Transformer (2024)0.00
• OER: Offline Experience Replay For Continual Offline Reinforcement Learning (2023)3.58
• Harmodt: Harmony Multi-task Decision Transformer For Offline Reinforcement Learning (2024)0.00
• Belief-based Offline Reinforcement Learning For Delay-robust Policy Optimization (2025)0.00
• Same State, Different Task: Continual Reinforcement Learning Without Interference (2021)0.00
• Using Curiosity For An Even Representation Of Tasks In Continual Offline Reinforcement Learning (2023)0.00
• Low-pass Recurrent Neural Networks - A Memory Architecture For Longer-term Correlation Discovery (2018)0.00
• Solving Continual Offline RL Through Selective Weights Activation On Aligned Spaces (2024)0.00