Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.14990 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915482443972608 |
|---|---|
| author | Tomilin, Tristan Boogaard, Luka van den Garcin, Samuel Grooten, Bram Fang, Meng Du, Yali Pechenizkiy, Mykola |
| author_facet | Tomilin, Tristan Boogaard, Luka van den Garcin, Samuel Grooten, Bram Fang, Meng Du, Yali Pechenizkiy, Mykola |
| contents | Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms, with environment availability strongly impacting research. One particularly underexplored intersection is continual learning (CL) in cooperative multi-agent settings. To remedy this, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark tailored for continual multi-agent reinforcement learning (CMARL). Existing CL benchmarks run environments on the CPU, leading to computational bottlenecks and limiting the length of task sequences. MEAL leverages JAX for GPU acceleration, enabling continual learning across sequences of 100 tasks on a standard desktop PC in a few hours. We show that naively combining popular CL and MARL methods yields strong performance on simple environments, but fails to scale to more complex settings requiring sustained coordination and adaptation. Our ablation study identifies architectural and algorithmic features critical for CMARL on MEAL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14990 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning Tomilin, Tristan Boogaard, Luka van den Garcin, Samuel Grooten, Bram Fang, Meng Du, Yali Pechenizkiy, Mykola Artificial Intelligence Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms, with environment availability strongly impacting research. One particularly underexplored intersection is continual learning (CL) in cooperative multi-agent settings. To remedy this, we introduce MEAL (Multi-agent Environments for Adaptive Learning), the first benchmark tailored for continual multi-agent reinforcement learning (CMARL). Existing CL benchmarks run environments on the CPU, leading to computational bottlenecks and limiting the length of task sequences. MEAL leverages JAX for GPU acceleration, enabling continual learning across sequences of 100 tasks on a standard desktop PC in a few hours. We show that naively combining popular CL and MARL methods yields strong performance on simple environments, but fails to scale to more complex settings requiring sustained coordination and adaptation. Our ablation study identifies architectural and algorithmic features critical for CMARL on MEAL. |
| title | MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2506.14990 |