Shared-unique Features And Task-aware Prioritized Sampling On Multi-task Reinforcement Learning

Abstract

We observe that current state-of-the-art (SOTA) methods suffer from the performance imbalance issue when performing multi-task reinforcement learning (MTRL) tasks. While these methods may achieve impressive performance on average, they perform extremely poorly on a few tasks. To address this, we propose a new and effective method called STARS, which consists of two novel strategies: a shared-unique feature extractor and task-aware prioritized sampling. First, the shared-unique feature extractor learns both shared and task-specific features to enable better synergy of knowledge between different tasks. Second, the task-aware sampling strategy is combined with the prioritized experience replay for efficient learning on tasks with poor performance. The effectiveness and stability of our STARS are verified through experiments on the mainstream Meta-World benchmark. From the results, our STARS statistically outperforms current SOTA methods and alleviates the performance imbalance issue. Bes

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylin2024shared

Related papers

• Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning With Diverse Tasks (2024)0.00
• Coreset-based Task Selection For Sample-efficient Meta-reinforcement Learning (2025)0.00
• A Model-based Approach For Sample-efficient Multi-task Reinforcement Learning (2019)0.00
• Efficient Reinforcement Learning In Resource Allocation Problems Through Permutation Invariant Multi-task Learning (2021)5.24
• Selectively Sharing Experiences Improves Multi-agent Reinforcement Learning (2023)4.61
• Higher Replay Ratio Empowers Sample-efficient Multi-agent Reinforcement Learning (2024)0.00
• Provable Multi-task Reinforcement Learning: A Representation Learning Framework With Low Rank Rewards (2026)0.00
• Boosting Exploration In Multi-task Reinforcement Learning Using Adversarial Networks (2022)0.00