Papers › HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

5 Dec 2024arXiv:2412.04233archive 2025-07-28

Kale-ab Abebe Tessera, Arrasy Rahman, Amos Storkey, Stefano V. Albrecht

Adaptability to specialised or homogeneous behaviours is critical in cooperative multi-agent reinforcement learning (MARL). Parameter sharing (PS) techniques, common for efficient adaptation, often limit behavioural diversity due to cross-agent gradient interference, which we show can be exacerbated by the coupling of observations and agent IDs. Current remedies typically add complexity through altered objectives, manual preset diversity levels, or sequential updates. We ask: can shared policies adapt without these complexities? We propose HyperMARL, a PS approach using hypernetworks for dynamic agent-specific parameters, without altering the RL objective or requiring preset diversity levels. HyperMARL's explicit decoupling of observation- and agent-conditioned gradients empirically reduces policy gradient variance, facilitates shared-policy adaptation (including specialisation), and helps mitigate cross-agent interference. Across diverse MARL benchmarks (up to 20 agents), requiring homogeneous, heterogeneous, or mixed behaviours, HyperMARL achieves competitive performance against key baselines -- fully shared, non-parameter sharing, and three diversity-promoting methods -- while preserving behavioural diversity comparable to non-parameter sharing. These findings establish HyperMARL as a versatile approach for adaptive MARL. The code is publicly available at https://github.com/KaleabTessera/HyperMARL.

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="2412.04233")

Code

Syntology Ran 2 of 26 code samples harvested from 1 repository linked to this paper; 24 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 26 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

kaleabtessera/hypermarl officialmentioned in papermentioned 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

26 samples harvested; 2 ran; 0 honoured the contract we drafted; 24 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.

1ran · our draft was wrong
1ran
24unverified

Licence: 0 of the 26 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 kaleabtessera/hypermarl. “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.

MLPHyperNetwork kaleabtessera/hypermarl/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py official repository ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1752721940e08b00 · report
initialize_metrics_storage kaleabtessera/hypermarl/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py official repository ran · our draft was wrong Apache-2.0 (permissive) · c65ecc507b666ec7 · report
HyperNetType kaleabtessera/hypermarl/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py official repository unverified Apache-2.0 (permissive) · fc2635d1edc5744c · report
batchify KaleabTessera/HyperMARL/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py official repository unverified Apache-2.0 (permissive) · 199a93e72a7ef243 · report
batchify KaleabTessera/HyperMARL/baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py official repository unverified Apache-2.0 (permissive) · 3425052e6f822468 · report
calculate_gradient_metrics KaleabTessera/HyperMARL/baselines/IPPO/ppo.py official repository unverified Apache-2.0 (permissive) · cef5d3f8f582f11c · report
check_rows_orthogonal kaleabtessera/hypermarl/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py official repository unverified Apache-2.0 (permissive) · bcb0454a347fa497 · report
check_rows_orthogonal KaleabTessera/HyperMARL/baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py official repository unverified Apache-2.0 (permissive) · 81333b03547dec15 · report
check_rows_orthogonal KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · 39a086f00e865a15 · report
check_rows_orthogonal KaleabTessera/HyperMARL/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py official repository unverified Apache-2.0 (permissive) · 74c4e3ca9e6165a8 · report
check_rows_orthogonal KaleabTessera/HyperMARL/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · 33389a53f0258aa8 · report
get_update_fn_ff_ppo KaleabTessera/HyperMARL/baselines/IPPO/ppo.py official repository unverified Apache-2.0 (permissive) · 5acb214ca13472b6 · report
get_update_fn_rec KaleabTessera/HyperMARL/baselines/IPPO/ppo.py official repository unverified Apache-2.0 (permissive) · 713c47ef2b9b7452 · report
initialize_metrics_storage KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · 9448f3eb55de759e · report
initialize_metrics_storage KaleabTessera/HyperMARL/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · ddd7b106ce20543f · report
initialize_metrics_storage KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_nps.py official repository unverified Apache-2.0 (permissive) · f751066367a6eef7 · report
initialize_metrics_storage KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_shared_weights.py official repository unverified Apache-2.0 (permissive) · 56878577396cbd05 · report
make KaleabTessera/HyperMARL/jaxmarl/registration.py official repository unverified Apache-2.0 (permissive) · e322b3637217c7eb · report
play_episode KaleabTessera/HyperMARL/baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py official repository unverified Apache-2.0 (permissive) · 3ca3980ead7240ce · report
unbatchify KaleabTessera/HyperMARL/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py official repository unverified Apache-2.0 (permissive) · 6febd2e7a2d28568 · report
unbatchify KaleabTessera/HyperMARL/baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py official repository unverified Apache-2.0 (permissive) · 3e5d2a25923e7af8 · report
update_metrics kaleabtessera/hypermarl/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py official repository unverified Apache-2.0 (permissive) · 3b65097bdfeabc03 · report
update_metrics KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · 1ebe26893033a16f · report
update_metrics KaleabTessera/HyperMARL/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py official repository unverified Apache-2.0 (permissive) · 34e77efd01e92918 · report
update_metrics KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_nps.py official repository unverified Apache-2.0 (permissive) · e1710023a6660530 · report
update_metrics KaleabTessera/HyperMARL/baselines/IPPO/ippo_ff_shared_weights.py official repository unverified Apache-2.0 (permissive) · 6891de2d310cbd35 · report

Tasks

DiversityMulti-agent Reinforcement Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

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