CAMAR: Continuous Actions Multi-Agent Routing
Not on the map. Why?
Abstract (arXiv)
Multi-agent reinforcement learning (MARL) is a powerful paradigm for solving cooperative and competitive decision-making problems. While many MARL benchmarks have been proposed, few combine continuous state and action spaces with challenging coordination and planning tasks. We introduce CAMAR, a new MARL benchmark designed explicitly for multi-agent pathfinding in environments with continuous actions. CAMAR supports cooperative and competitive interactions between agents and runs efficiently at up to 100,000 environment steps per second. We also propose a three-tier evaluation protocol to better track algorithmic progress and enable deeper analysis of performance. In addition, CAMAR allows the integration of classical planning methods such as RRT and RRT* into MARL pipelines. We use them as standalone baselines and combine RRT* with popular MARL algorithms to create hybrid approaches. We provide a suite of test scenarios and benchmarking tools to ensure reproducibility and fair comparison. Experiments show that CAMAR presents a challenging and realistic testbed for the MARL community.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 27 of its 47 references that are in the map. First posted on arXiv 18 Aug 2025.
Builds on
27 of 47 references.
References · 27
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
- 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
- 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
- 2019The StarCraft Multi-Agent Challengecited by 589
- 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
- 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
- 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 257
- 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 207
- 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 118
- 2020Flightmare: A Flexible Quadrotor Simulatorcited by 69
- 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 63
- 2020PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelongcited by 61
15 more
- 2022Nocturne: a scalable driving benchmark for bringing multi-agent learning one step closer to the real worldcited by 56
- 2023Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXcited by 52
- 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 48
- 2020Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learningcited by 36
- 2023Heterogeneous Multi-Robot Reinforcement Learningcited by 34
- 2023BenchMARL: Benchmarking Multi-Agent Reinforcement Learningcited by 31
- 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discoverycited by 29
- 2023Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learningcited by 27
- 2024PufferLib: Making Reinforcement Learning Libraries and Environments Play Nicecited by 22
- 2024POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfindingcited by 20
- 2024MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scalecited by 17
- 2022POGEMA: Partially Observable Grid Environment for Multiple Agentscited by 6
- 2022Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstaclescited by 6
- 2025Advancing MAPF Toward the Real World: A Scalable Multi-Agent Realistic Testbed (SMART)cited by 5
- 2024Multi-Agent Path Finding with Real Robot Dynamics and Interdependent Tasks for Automated Warehousescited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.