{"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/fanin-init","entry":"fanin_init","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":12,"n_papers_ran":10,"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":9,"n_samples_ran":6,"n_samples_fingerprinted":4,"n_places":14,"n_places_pointer_only":8,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":3,"ran":1,"unverified":3},"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":"2603.12087","paper":"/paper/arxiv-2603-12087","title":"Cross-Domain Policy Optimization via Bellman Consistency and Hybrid Critics","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"dmksjfl/PAR","path":"algo/utils.py","file_url":"https://github.com/dmksjfl/PAR/blob/HEAD/algo/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b5a164602274858","mcp_get_code":{"code_sha256":"3b5a164602274858"}},{"arxiv_id":"2506.12822","paper":"/paper/enhancing-rating-based-reinforcement-learning","title":"Enhancing Rating-Based Reinforcement Learning to Effectively Leverage Feedback from Large Vision-Language Models","date":"2025-06-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tunglm2203/erlvlm","path":"conv_net.py","file_url":"https://github.com/tunglm2203/erlvlm/blob/HEAD/conv_net.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3f01f9fd0d0c237e","mcp_get_code":{"code_sha256":"3f01f9fd0d0c237e"}},{"arxiv_id":"2505.12628","paper":"/paper/dual-agent-reinforcement-learning-for","title":"Dual-Agent Reinforcement Learning for Automated Feature Generation","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"extess0/DARL","path":"feature_generation/embedding_policy.py","file_url":"https://github.com/extess0/DARL/blob/HEAD/feature_generation/embedding_policy.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4e1854ae8e15b098","mcp_get_code":{"code_sha256":"4e1854ae8e15b098"}},{"arxiv_id":"2410.20750","paper":"/paper/odrl-a-benchmark-for-off-dynamics","title":"ODRL: A Benchmark for Off-Dynamics Reinforcement Learning","date":"2024-10-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"offdynamicsrl/off-dynamics-rl","path":"algo/utils.py","file_url":"https://github.com/offdynamicsrl/off-dynamics-rl/blob/HEAD/algo/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3b5a164602274858","mcp_get_code":{"code_sha256":"3b5a164602274858"}},{"arxiv_id":"2402.04080","paper":"/paper/entropy-regularized-diffusion-policy-with-q","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ruoqizzz/entropy-offlineRL","path":"utils/pytorch_util.py","file_url":"https://github.com/ruoqizzz/entropy-offlineRL/blob/HEAD/utils/pytorch_util.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3b5a164602274858","mcp_get_code":{"code_sha256":"3b5a164602274858"}},{"arxiv_id":"2309.04612","paper":"/paper/self-optimizing-feature-generation-via","title":"Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing","date":"2023-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yingwangyang/hrc_feature_cross","path":"model.py","file_url":"https://github.com/yingwangyang/hrc_feature_cross/blob/HEAD/model.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7b6772b561c055e2","mcp_get_code":{"code_sha256":"7b6772b561c055e2"}},{"arxiv_id":"1908.00821","paper":"/paper/learning-lightweight-lane-detection-cnns-by","title":"Learning Lightweight Lane Detection CNNs by Self Attention Distillation","date":"2019-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"NOHYC/autonomous_driving_car_project","path":"SIM/catkin_ws/src/project/src/ddpg_stage.py","file_url":"https://github.com/NOHYC/autonomous_driving_car_project/blob/HEAD/SIM/catkin_ws/src/project/src/ddpg_stage.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0d0842514b1844a1","mcp_get_code":{"code_sha256":"0d0842514b1844a1"}},{"arxiv_id":"1907.11625","paper":"/paper/learning-policies-for-social-network","title":"Influence maximization in unknown social networks: Learning Policies for Effective Graph Sampling","date":"2019-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kage08/graph_sample_rl","path":"diffpool/utils.py","file_url":"https://github.com/kage08/graph_sample_rl/blob/HEAD/diffpool/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02725759d7e0f793","mcp_get_code":{"code_sha256":"02725759d7e0f793"}},{"arxiv_id":"1906.09807","paper":"/paper/proximal-distilled-evolutionary-reinforcement","title":"Proximal Distilled Evolutionary Reinforcement Learning","date":"2019-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crisbodnar/pderl","path":"core/ddpg.py","file_url":"https://github.com/crisbodnar/pderl/blob/HEAD/core/ddpg.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6c6e3e93f6af32d6","mcp_get_code":{"code_sha256":"6c6e3e93f6af32d6"}},{"arxiv_id":"1906.09807","paper":"/paper/proximal-distilled-evolutionary-reinforcement","title":"Proximal Distilled Evolutionary Reinforcement Learning","date":"2019-06-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"crisbodnar/pderl","path":"core/mod_utils.py","file_url":"https://github.com/crisbodnar/pderl/blob/HEAD/core/mod_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bbc615c1230eade5","mcp_get_code":{"code_sha256":"bbc615c1230eade5"}},{"arxiv_id":"1805.07917","paper":"/paper/evolution-guided-policy-gradient-in","title":"Evolution-Guided Policy Gradient in Reinforcement Learning","date":"2018-05-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lyp741/Pytorch-ERL","path":"pytorch-erl.py","file_url":"https://github.com/lyp741/Pytorch-ERL/blob/HEAD/pytorch-erl.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"825ecb6732e9fc31","mcp_get_code":{"code_sha256":"825ecb6732e9fc31"}},{"arxiv_id":"1705.05363","paper":"/paper/curiosity-driven-exploration-by-self","title":"Curiosity-driven Exploration by Self-supervised Prediction","date":"2017-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HaozheJasper/CBRL_KDD22","path":"python/model.py","file_url":"https://github.com/HaozheJasper/CBRL_KDD22/blob/HEAD/python/model.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"3f01f9fd0d0c237e","mcp_get_code":{"code_sha256":"3f01f9fd0d0c237e"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"825ecb6732e9fc31","mcp_get_code":{"code_sha256":"825ecb6732e9fc31"}},{"arxiv_id":"1509.02971","paper":"/paper/continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fshamshirdar/pytorch-rdpg","path":"rdpg.py","file_url":"https://github.com/fshamshirdar/pytorch-rdpg/blob/HEAD/rdpg.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0d0842514b1844a1","mcp_get_code":{"code_sha256":"0d0842514b1844a1"}}]}