{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/hypermarl-adaptive-hypernetworks-for-multi","title":"HyperMARL: Adaptive Hypernetworks for Multi-Agent RL","arxiv_id":"2412.04233","date":"2024-12-05","proceeding":null,"authors":["Kale-ab Abebe Tessera","Arrasy Rahman","Amos Storkey","Stefano V. Albrecht"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2412.04233v3","url_pdf":"https://arxiv.org/pdf/2412.04233v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"hypermarl-adaptive-hypernetworks-for-multi","repo_url":"https://github.com/kaleabtessera/hypermarl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.04233","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.04233"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/KaleabTessera/HyperMARL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kaleabtessera/hypermarl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":24},"by_repo_kind":{"official":{"samples":26,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1752721940e08b00","entry":"MLPHyperNetwork","repo":"kaleabtessera/hypermarl","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","file_url":"https://github.com/kaleabtessera/hypermarl/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1752721940e08b00"}},{"code_sha256_prefix":"c65ecc507b666ec7","entry":"initialize_metrics_storage","repo":"kaleabtessera/hypermarl","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","file_url":"https://github.com/kaleabtessera/hypermarl/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c65ecc507b666ec7"}},{"code_sha256_prefix":"fc2635d1edc5744c","entry":"HyperNetType","repo":"kaleabtessera/hypermarl","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","file_url":"https://github.com/kaleabtessera/hypermarl/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc2635d1edc5744c"}},{"code_sha256_prefix":"199a93e72a7ef243","entry":"batchify","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"199a93e72a7ef243"}},{"code_sha256_prefix":"3425052e6f822468","entry":"batchify","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3425052e6f822468"}},{"code_sha256_prefix":"cef5d3f8f582f11c","entry":"calculate_gradient_metrics","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ppo.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cef5d3f8f582f11c"}},{"code_sha256_prefix":"bcb0454a347fa497","entry":"check_rows_orthogonal","repo":"kaleabtessera/hypermarl","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","file_url":"https://github.com/kaleabtessera/hypermarl/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bcb0454a347fa497"}},{"code_sha256_prefix":"81333b03547dec15","entry":"check_rows_orthogonal","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81333b03547dec15"}},{"code_sha256_prefix":"39a086f00e865a15","entry":"check_rows_orthogonal","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39a086f00e865a15"}},{"code_sha256_prefix":"74c4e3ca9e6165a8","entry":"check_rows_orthogonal","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74c4e3ca9e6165a8"}},{"code_sha256_prefix":"33389a53f0258aa8","entry":"check_rows_orthogonal","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"33389a53f0258aa8"}},{"code_sha256_prefix":"5acb214ca13472b6","entry":"get_update_fn_ff_ppo","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ppo.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5acb214ca13472b6"}},{"code_sha256_prefix":"713c47ef2b9b7452","entry":"get_update_fn_rec","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ppo.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ppo.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"713c47ef2b9b7452"}},{"code_sha256_prefix":"9448f3eb55de759e","entry":"initialize_metrics_storage","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9448f3eb55de759e"}},{"code_sha256_prefix":"ddd7b106ce20543f","entry":"initialize_metrics_storage","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ddd7b106ce20543f"}},{"code_sha256_prefix":"f751066367a6eef7","entry":"initialize_metrics_storage","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_nps.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_nps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f751066367a6eef7"}},{"code_sha256_prefix":"56878577396cbd05","entry":"initialize_metrics_storage","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56878577396cbd05"}},{"code_sha256_prefix":"e322b3637217c7eb","entry":"make","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"jaxmarl/registration.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/jaxmarl/registration.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e322b3637217c7eb"}},{"code_sha256_prefix":"3ca3980ead7240ce","entry":"play_episode","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/Matrix_Game/specialisation_game_with_state_jax_hypermarl_base.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ca3980ead7240ce"}},{"code_sha256_prefix":"6febd2e7a2d28568","entry":"unbatchify","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_rnn_smax_mlp_hypernets_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6febd2e7a2d28568"}},{"code_sha256_prefix":"3e5d2a25923e7af8","entry":"unbatchify","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/MAPPO/mappo_rnn_smax_mlp_hypernets_eval.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e5d2a25923e7af8"}},{"code_sha256_prefix":"3b65097bdfeabc03","entry":"update_metrics","repo":"kaleabtessera/hypermarl","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","file_url":"https://github.com/kaleabtessera/hypermarl/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_mlp_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3b65097bdfeabc03"}},{"code_sha256_prefix":"1ebe26893033a16f","entry":"update_metrics","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1ebe26893033a16f"}},{"code_sha256_prefix":"34e77efd01e92918","entry":"update_metrics","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/MAPPO/mappo_ff_shared_weights_linear_hypernets.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"34e77efd01e92918"}},{"code_sha256_prefix":"e1710023a6660530","entry":"update_metrics","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_nps.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_nps.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e1710023a6660530"}},{"code_sha256_prefix":"6891de2d310cbd35","entry":"update_metrics","repo":"KaleabTessera/HyperMARL","repo_kind":"official","path":"baselines/IPPO/ippo_ff_shared_weights.py","file_url":"https://github.com/KaleabTessera/HyperMARL/blob/HEAD/baselines/IPPO/ippo_ff_shared_weights.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6891de2d310cbd35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}