mlsanityData to 7 Oct 2026

TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning

arXiv 2602.01665 ↗First posted 2 Feb 2026cs.MA cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (MARL) algorithms. While existing benchmarks highlight critical challenges, they often lack the modularity required to design custom evaluation scenarios. We introduce the Totally Accelerated Battle Simulator in JAX (TABX), a high-throughput sandbox designed for reconfigurable multi-agent tasks. TABX provides granular control over environmental parameters, permitting a systematic investigation into emergent agent behaviors and algorithmic trade-offs across a diverse spectrum of task complexities. Leveraging JAX for hardware-accelerated execution on GPUs, TABX enables massive parallelization and significantly reduces computational overhead. By providing a fast, extensible, and easily customized framework, TABX facilitates the study of MARL agents in complex structured domains and serves as a scalable foundation for future research. Our code is available at: https://github.com/ku-dmlab/TABX.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 40 of its 44 references that are in the map. First posted on arXiv 2 Feb 2026.

Builds on

40 of 44 references.

References · 40

  1. 2016Layer Normalizationcited by 5,579
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,519
  4. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  5. 2018Exploration by Random Network Distillationcited by 966
  6. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  7. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  8. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
  9. 2019The StarCraft Multi-Agent Challengecited by 589
  10. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 475
  11. 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 372
  12. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 345
28 more
  1. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 320
  2. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 281
  3. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 260
  4. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 257
  5. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  6. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 209
  7. 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 194
  8. 2020Prioritized Level Replaycited by 190
  9. 2019Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutionscited by 182
  10. 2015Multiagent Cooperation and Competition with Deep Reinforcement Learningcited by 180
  11. 2019OpenSpiel: A Framework for Reinforcement Learning in Gamescited by 180
  12. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 180
  13. 2022Evolving Curricula with Regret-Based Environment Designcited by 166
  14. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 118
  15. 2021Learning One Representation to Optimize All Rewardscited by 110
  16. 2021Replay-Guided Adversarial Environment Designcited by 108
  17. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 80
  18. 2024Simplifying Deep Temporal Difference Learningcited by 71
  19. 2017MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligencecited by 69
  20. 2023JaxMARL: Multi-Agent RL Environments and Algorithms in JAXcited by 59
  21. 2017Markov Decision Processes with Continuous Side Informationcited by 54
  22. 2023XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXcited by 54
  23. 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learningcited by 45
  24. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Taskscited by 40
  25. 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discoverycited by 29
  26. 2024Accelerating Goal-Conditioned RL Algorithms and Researchcited by 18
  27. 2024JaxUED: A simple and useable UED library in Jaxcited by 10
  28. 2025Efficient Multi-Task Reinforcement Learning with Cross-Task Policy Guidancecited by 3

Built on by

Not cited yet.