{"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":"/code/onehot-from-logits","entry":"onehot_from_logits","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":10,"n_papers_ran":8,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":5,"n_samples_ran":3,"n_samples_fingerprinted":3,"n_places":11,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":2},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2506.11285","paper":"/paper/shapley-machine-a-game-theoretic-framework","title":"Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork","date":"2025-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hsvgbkhgbv/shapley-machine-naht","path":"src/controllers/maddpg_controller.py","file_url":"https://github.com/hsvgbkhgbv/shapley-machine-naht/blob/HEAD/src/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2410.08540","paper":"/paper/kaleidoscope-learnable-masks-for","title":"Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning","date":"2024-10-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LXXXXR/Kaleidoscope","path":"Kalei_MPE/src/controllers/maddpg_controller.py","file_url":"https://github.com/LXXXXR/Kaleidoscope/blob/HEAD/Kalei_MPE/src/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2410.03997","paper":null,"title":"arXiv:2410.03997","date":null,"month_inferred_from_arxiv_id":"2024-10","title_source":null,"repo":"paulzyzy/YOLO-MARL","path":"YOLO-MARL/src/controllers/maddpg_controller.py","file_url":"https://github.com/paulzyzy/YOLO-MARL/blob/HEAD/YOLO-MARL/src/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2212.05331","paper":"/paper/effects-of-spectral-normalization-in-multi","title":"Effects of Spectral Normalization in Multi-agent Reinforcement Learning","date":"2022-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kinalmehta/epymarl_spectral","path":"src_spectral/controllers/maddpg_controller.py","file_url":"https://github.com/kinalmehta/epymarl_spectral/blob/HEAD/src_spectral/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2210.06835","paper":"/paper/multi-agent-dynamic-algorithm-configuration","title":"Multi-agent Dynamic Algorithm Configuration","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lamda-bbo/madac","path":"algos/madac/controllers/maddpg_controller.py","file_url":"https://github.com/lamda-bbo/madac/blob/HEAD/algos/madac/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2006.09447","paper":"/paper/opponent-modelling-with-local-information","title":"Agent Modelling under Partial Observability for Deep Reinforcement Learning","date":"2020-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uoe-agents/LIAM","path":"double_speaker_listener/misc.py","file_url":"https://github.com/uoe-agents/LIAM/blob/HEAD/double_speaker_listener/misc.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"2006.07869","paper":"/paper/comparative-evaluation-of-multi-agent-deep","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","date":"2020-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dtabas/epymarl","path":"src/controllers/maddpg_controller.py","file_url":"https://github.com/dtabas/epymarl/blob/HEAD/src/controllers/maddpg_controller.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"046b92243aae4f76","mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"arxiv_id":"1902.04043","paper":"/paper/the-starcraft-multi-agent-challenge","title":"The StarCraft Multi-Agent Challenge","date":"2019-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kcorder/qmix_variants","path":"src/components/action_selectors.py","file_url":"https://github.com/kcorder/qmix_variants/blob/HEAD/src/components/action_selectors.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"code_sha256_prefix":"d2a8ffa31f7e13c8","mcp_get_code":{"code_sha256":"d2a8ffa31f7e13c8"}},{"arxiv_id":"1810.02912","paper":"/paper/actor-attention-critic-for-multi-agent","title":"Actor-Attention-Critic for Multi-Agent Reinforcement Learning","date":"2018-10-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shariqiqbal2810/MAAC","path":"utils/misc.py","file_url":"https://github.com/shariqiqbal2810/MAAC/blob/HEAD/utils/misc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e47eaea5616287c6","mcp_get_code":{"code_sha256":"e47eaea5616287c6"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Chan1998/MAAC","path":"algorithms/attention_sac.py","file_url":"https://github.com/Chan1998/MAAC/blob/HEAD/algorithms/attention_sac.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"5290a0543b38c4dc","mcp_get_code":{"code_sha256":"5290a0543b38c4dc"}},{"arxiv_id":"1706.02275","paper":"/paper/multi-agent-actor-critic-for-mixed","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","date":"2017-06-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Yutongamber/MADDPG","path":"maddpg-pytorch/algorithms/maddpg.py","file_url":"https://github.com/Yutongamber/MADDPG/blob/HEAD/maddpg-pytorch/algorithms/maddpg.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f925a8c266bb2532","mcp_get_code":{"code_sha256":"f925a8c266bb2532"}}]}