mlsanityData to 14 Oct 2026

marl-jax: Multi-Agent Reinforcement Leaning Framework

arXiv 2303.13808 ↗First posted 24 Mar 2023cs.MA cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Recent advances in Reinforcement Learning (RL) have led to many exciting applications. These advancements have been driven by improvements in both algorithms and engineering, which have resulted in faster training of RL agents. We present marl-jax, a multi-agent reinforcement learning software package for training and evaluating social generalization of the agents. The package is designed for training a population of agents in multi-agent environments and evaluating their ability to generalize to diverse background agents. It is built on top of DeepMind's JAX ecosystem~citedeepmind2020jax and leverages the RL ecosystem developed by DeepMind. Our framework marl-jax is capable of working in cooperative and competitive, simultaneous-acting environments with multiple agents. The package offers an intuitive and user-friendly command-line interface for training a population and evaluating its generalization capabilities. In conclusion, marl-jax provides a valuable resource for researchers interested in exploring social generalization in the context of MARL. The open-source code for marl-jax is available at: hrefhttps://github.com/kinalmehta/marl-jaxhttps://github.com/kinalmehta/marl-jax

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 19 of its 26 references that are in the map. First posted on arXiv 24 Mar 2023.

Builds on

19 of 26 references.

References · 19

  1. 2016OpenAI Gymcited by 1,736
  2. 2018IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architecturescited by 883
  3. 2019The StarCraft Multi-Agent Challengecited by 597
  4. 2019On the Utility of Learning about Humans for Human-AI Coordinationcited by 349
  5. 2020PettingZoo: Gym for Multi-Agent Reinforcement Learningcited by 220
  6. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  7. 2021Open-Ended Learning Leads to Generally Capable Agentscited by 182
  8. 2020Acme: A Research Framework for Distributed Reinforcement Learningcited by 146
  9. 2018Dopamine: A Research Framework for Deep Reinforcement Learningcited by 122
  10. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  11. 2022Melting Pot 2.0cited by 40
  12. 2021Podracer architectures for scalable Reinforcement Learningcited by 38
7 more
  1. 2021Reverb: A Framework For Experience Replaycited by 27
  2. 2021MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learningcited by 23
  3. 2022Generalization in Cooperative Multi-Agent Systemscited by 19
  4. 2021Mava: a research library for distributed multi-agent reinforcement learning in JAXcited by 16
  5. 2021Launchpad: A Programming Model for Distributed Machine Learning Researchcited by 14
  6. 2021PantheonRL: A MARL Library for Dynamic Training Interactionscited by 10
  7. 2019Options as responses: Grounding behavioural hierarchies in multi-agent RLcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Alpha Elimination: Using Deep Reinforcement Learning to Reduce Fill-In during Sparse Matrix Decompositioncited by 4