{"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/mlpnetwork","entry":"MLPNetwork","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":6,"n_papers_ran":6,"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":6,"n_samples_ran":6,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"unverified":0},"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":"2605.24862","paper":"/paper/arxiv-2605-24862","title":"Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"zq2r/V2A","path":"algo/offline_offline/v2a_igdf.py","file_url":"https://github.com/zq2r/V2A/blob/HEAD/algo/offline_offline/v2a_igdf.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"df54328b8327c1f5","mcp_get_code":{"code_sha256":"df54328b8327c1f5"}},{"arxiv_id":"2512.02486","paper":"/paper/arxiv-2512-02486","title":"Dual-Robust Cross-Domain Offline Reinforcement Learning Against Dynamics Shifts","date":null,"month_inferred_from_arxiv_id":"2025-12","title_source":"syntology","repo":"zq2r/DROCO","path":"algo/offline_offline/droco.py","file_url":"https://github.com/zq2r/DROCO/blob/HEAD/algo/offline_offline/droco.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c62cb3511f9129eb","mcp_get_code":{"code_sha256":"c62cb3511f9129eb"}},{"arxiv_id":"2405.19690","paper":"/paper/diffusion-policies-creating-a-trust-region","title":"Diffusion Policies creating a Trust Region for Offline Reinforcement Learning","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tianyucodings/diffusion_trusted_q_learning","path":"agents/dtql.py","file_url":"https://github.com/tianyucodings/diffusion_trusted_q_learning/blob/HEAD/agents/dtql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b4d20c11cf5cfc46","mcp_get_code":{"code_sha256":"b4d20c11cf5cfc46"}},{"arxiv_id":"2307.11685","paper":"/paper/towards-generalizable-reinforcement-learning","title":"Towards Generalizable Reinforcement Learning for Trade Execution","date":"2023-05-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhangchuheng123/RL4Execution","path":"code/policy_cate.py","file_url":"https://github.com/zhangchuheng123/RL4Execution/blob/HEAD/code/policy_cate.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"875c961ba78603c3","mcp_get_code":{"code_sha256":"875c961ba78603c3"}},{"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","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d91c262ff01c1192","mcp_get_code":{"code_sha256":"d91c262ff01c1192"}},{"arxiv_id":"1312.5602","paper":"/paper/playing-atari-with-deep-reinforcement","title":"Playing Atari with Deep Reinforcement Learning","date":"2013-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chandar-lab/RLHive","path":"hive/agents/qnets/atari/nature_atari_dqn.py","file_url":"https://github.com/chandar-lab/RLHive/blob/HEAD/hive/agents/qnets/atari/nature_atari_dqn.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7af2befd6fd71b28","mcp_get_code":{"code_sha256":"7af2befd6fd71b28"}}]}