Papers › JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

JaxMARL: Multi-Agent RL Environments and Algorithms in JAX

16 Nov 2023arXiv:2311.10090archive 2025-07-28

Alexander Rutherford, Benjamin Ellis, Matteo Gallici, Jonathan Cook, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Ravi Hammond, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, Chris Lu, Jakob Nicolaus Foerster

Benchmarks are crucial in the development of machine learning algorithms, with available environments significantly influencing reinforcement learning (RL) research. Traditionally, RL environments run on the CPU, which limits their scalability with typical academic compute. However, recent advancements in JAX have enabled the wider use of hardware acceleration, enabling massively parallel RL training pipelines and environments. While this has been successfully applied to single-agent RL, it has not yet been widely adopted for multi-agent scenarios. In this paper, we present JaxMARL, the first open-source, Python-based library that combines GPU-enabled efficiency with support for a large number of commonly used MARL environments and popular baseline algorithms. Our experiments show that, in terms of wall clock time, our JAX-based training pipeline is around 14 times faster than existing approaches, and up to 12500x when multiple training runs are vectorized. This enables efficient and thorough evaluations, potentially alleviating the evaluation crisis in the field. We also introduce and benchmark SMAX, a JAX-based approximate reimplementation of the popular StarCraft Multi-Agent Challenge, which removes the need to run the StarCraft II game engine. This not only enables GPU acceleration, but also provides a more flexible MARL environment, unlocking the potential for self-play, meta-learning, and other future applications in MARL. The code is available at https://github.com/flairox/jaxmarl.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2311.10090")

Code

Syntology Ran 0 of 23 code samples harvested from 1 repository linked to this paper; 23 have no recorded run.

By repository: community (archive-listed): 23 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

flairox/jaxmarl officialmentioned in papermentioned on GitHubjaxApache-2.0 report
kfu02/jaxmarl mentioned on GitHubjaxApache-2.0 report
ucl-dark/pax mentioned on GitHubjaxApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

23 samples harvested; 0 ran; 0 honoured the contract we drafted; 23 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

23unverified

Licence: 0 of the 23 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from ucl-dark/pax. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

add_batch_dim ucl-dark/pax/pax/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 6b4576fe27ed0a8e · report
get_advantages ucl-dark/pax/pax/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 8d1fa95afa90b12b · report
global_setup ucl-dark/pax/pax/experiment.py community (archive-listed) unverified Apache-2.0 (permissive) · 7998dbf93494334f · report
make_GRU ucl-dark/pax/pax/agents/hyper/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · bdb8d47954719031 · report
make_GRU_hypernetwork ucl-dark/pax/pax/agents/hyper/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 61fc2fad0c403979 · report
make_GRU_ipd_att_network ucl-dark/pax/pax/agents/shaper_att/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 0a49d3ae85eecc1f · report
make_GRU_ipd_avg_network ucl-dark/pax/pax/agents/shaper_att/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · d64c512a602ec179 · report
make_GRU_ipd_network ucl-dark/pax/pax/agents/shaper_att/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 365cfd6131c2ac62 · report
make_coingame_network ucl-dark/pax/pax/agents/naive/network.py community (archive-listed) unverified Apache-2.0 (permissive) · 607630c430f35d26 · report
make_cournot_network ucl-dark/pax/pax/agents/ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · ba7cdb74da41663e · report
make_fishery_network ucl-dark/pax/pax/agents/ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c5f9da603bc1634 · report
make_ipd_network ucl-dark/pax/pax/agents/ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · db890d82d0ebeef0 · report
make_mfos_avg_network ucl-dark/pax/pax/agents/mfos_ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · d48299dc9766e894 · report
make_mfos_continuous_network ucl-dark/pax/pax/agents/mfos_ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · cb1865b00332fa19 · report
make_mfos_network ucl-dark/pax/pax/agents/mfos_ppo/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 2eb4d1417b0a6d2f · report
make_network ucl-dark/pax/pax/agents/hyper/networks.py community (archive-listed) unverified Apache-2.0 (permissive) · 019e1da94cf6b12f · report
make_network ucl-dark/pax/pax/agents/lola/network.py community (archive-listed) unverified Apache-2.0 (permissive) · 2cd8e496d080743d · report
make_network ucl-dark/pax/pax/agents/naive/network.py community (archive-listed) unverified Apache-2.0 (permissive) · bd3555b465d1974f · report
make_policy_network ucl-dark/pax/pax/agents/lola/network.py community (archive-listed) unverified Apache-2.0 (permissive) · d2a9587eacd4ae54 · report
make_rice_network ucl-dark/pax/pax/agents/naive/network.py community (archive-listed) unverified Apache-2.0 (permissive) · 8dfd96d7efaac91f · report
make_value_network ucl-dark/pax/pax/agents/lola/network.py community (archive-listed) unverified Apache-2.0 (permissive) · 7dfc7920e7654bda · report
reduce_outer_traj ucl-dark/pax/pax/runners/runner_marl_nplayer.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c175a3d42cc09ab · report
to_numpy ucl-dark/pax/pax/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 0c9e5aa92235c1ab · report

Tasks

Meta-LearningMulti-agent Reinforcement LearningReinforcement Learning (RL)StarcraftStarcraft II

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

BASE

1 archive method tag without a method page not shown.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections