Sharing Lifelong Reinforcement Learning Knowledge Via Modulating Masks

Abstract

Lifelong learning agents aim to learn multiple tasks sequentially over a lifetime. This involves the ability to exploit previous knowledge when learning new tasks and to avoid forgetting. Modulating masks, a specific type of parameter isolation approach, have recently shown promise in both supervised and reinforcement learning. While lifelong learning algorithms have been investigated mainly within a single-agent approach, a question remains on how multiple agents can share lifelong learning knowledge with each other. We show that the parameter isolation mechanism used by modulating masks is particularly suitable for exchanging knowledge among agents in a distributed and decentralized system of lifelong learners. The key idea is that the isolation of specific task knowledge to specific masks allows agents to transfer only specific knowledge on-demand, resulting in robust and effective distributed lifelong learning. We assume fully distributed and asynchronous scenarios with dynamic age

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynath2023sharing

Related papers

• Lifelong Reinforcement Learning With Modulating Masks (2022)0.00
• Continuous Coordination As A Realistic Scenario For Lifelong Learning (2021)0.00
• Kaleidoscope: Learnable Masks For Heterogeneous Multi-agent Reinforcement Learning (2024)2.26
• Scaling Distributed Multi-task Reinforcement Learning With Experience Sharing (2023)0.00
• Lipschitz Lifelong Reinforcement Learning (2020)8.35
• MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning (2025)0.00
• Deep Decentralized Multi-task Multi-agent Reinforcement Learning Under Partial Observability (2017)0.00
• Learning To Share In Multi-agent Reinforcement Learning (2021)0.00