Continuous Coordination As A Realistic Scenario For Lifelong Learning

Abstract

Current deep reinforcement learning (RL) algorithms are still highly task-specific and lack the ability to generalize to new environments. Lifelong learning (LLL), however, aims at solving multiple tasks sequentially by efficiently transferring and using knowledge between tasks. Despite a surge of interest in lifelong RL in recent years, the lack of a realistic testbed makes robust evaluation of LLL algorithms difficult. Multi-agent RL (MARL), on the other hand, can be seen as a natural scenario for lifelong RL due to its inherent non-stationarity, since the agents' policies change over time. In this work, we introduce a multi-agent lifelong learning testbed that supports both zero-shot and few-shot settings. Our setup is based on Hanabi -- a partially-observable, fully cooperative multi-agent game that has been shown to be challenging for zero-shot coordination. Its large strategy space makes it a desirable environment for lifelong RL tasks. We evaluate several recent MARL methods, an

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynekoei2021continuous

Related papers

• Lifelong Reinforcement Learning With Modulating Masks (2022)0.00
• Laser Learning Environment: A New Environment For Coordination-critical Multi-agent Tasks (2024)0.00
• Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In The Game Of Hanabi (2023)0.00
• Learning Curricula In Open-ended Worlds (2023)0.00
• Coordination-driven Learning In Multi-agent Problem Spaces (2018)0.00
• Stabilising Experience Replay For Deep Multi-agent Reinforcement Learning (2017)0.00
• Multi-agent Reinforcement Learning: A Selective Overview Of Theories And Algorithms (2019)21.85
• Language-driven Coordination And Learning In Multi-agent Simulation Environments (2025)0.00