{"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/normalize-states","entry":"normalize_states","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":15,"n_papers_ran":15,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":1,"n_places":15,"n_places_pointer_only":10,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2503.05306","paper":"/paper/adversarial-policy-optimization-for-offline","title":"Adversarial Policy Optimization for Offline Preference-based Reinforcement Learning","date":"2025-03-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2411.04138","paper":"/paper/networkgym-reinforcement-learning","title":"NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hmomin/CORL-compare","path":"algorithms/finetune/awac.py","file_url":"https://github.com/hmomin/CORL-compare/blob/HEAD/algorithms/finetune/awac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2410.22728","paper":"/paper/offline-behavior-distillation","title":"Offline Behavior Distillation","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"LeavesLei/OBD","path":"utils.py","file_url":"https://github.com/LeavesLei/OBD/blob/HEAD/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2408.04190","paper":"/paper/listwise-reward-estimation-for-offline","title":"Listwise Reward Estimation for Offline Preference-based Reinforcement Learning","date":"2024-08-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chwoong/LiRE","path":"algorithms/iql.py","file_url":"https://github.com/chwoong/LiRE/blob/HEAD/algorithms/iql.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2407.12448","paper":"/paper/energy-guided-diffusion-sampling-for-offline","title":"Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liuxhym/edis","path":"algorithms/cal_ql_edis.py","file_url":"https://github.com/liuxhym/edis/blob/HEAD/algorithms/cal_ql_edis.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2405.16907","paper":"/paper/gta-generative-trajectory-augmentation-with","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","date":"2024-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Jaewoopudding/GTA","path":"corl/shared/utils.py","file_url":"https://github.com/Jaewoopudding/GTA/blob/HEAD/corl/shared/utils.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2405.06192","paper":"/paper/contrastive-representation-for-data-filtering","title":"Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning","date":"2024-05-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"battlewen/igdf","path":"algorithms/igdf/igdf.py","file_url":"https://github.com/battlewen/igdf/blob/HEAD/algorithms/igdf/igdf.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2402.02423","paper":"/paper/uni-rlhf-universal-platform-and-benchmark","title":"Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2312.16248","paper":"/paper/xuance-a-comprehensive-and-unified-deep","title":"XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"agi-brain/xuance","path":"xuance/common/offline_util.py","file_url":"https://github.com/agi-brain/xuance/blob/HEAD/xuance/common/offline_util.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2310.12955","paper":"/paper/towards-robust-offline-reinforcement-learning","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","date":"2023-10-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2309.16973","paper":"/paper/towards-robust-offline-to-online","title":"Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness","date":"2023-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"battlewen/ro2o","path":"algorithms/finetune/awac.py","file_url":"https://github.com/battlewen/ro2o/blob/HEAD/algorithms/finetune/awac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2305.09836","paper":"/paper/revisiting-the-minimalist-approach-to-offline","title":"Revisiting the Minimalist Approach to Offline Reinforcement Learning","date":"2023-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"adamjelley/efficientofflinerl","path":"algorithms/any_percent_bc.py","file_url":"https://github.com/adamjelley/efficientofflinerl/blob/HEAD/algorithms/any_percent_bc.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2303.06614","paper":"/paper/synthetic-experience-replay-1","title":"Synthetic Experience Replay","date":"2023-03-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2210.07105","paper":"/paper/corl-research-oriented-deep-offline-1","title":"CORL: Research-oriented Deep Offline Reinforcement Learning Library","date":"2022-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tinkoff-ai/CORL","path":"algorithms/offline/awac.py","file_url":"https://github.com/tinkoff-ai/CORL/blob/HEAD/algorithms/offline/awac.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}},{"arxiv_id":"2106.06860","paper":"/paper/a-minimalist-approach-to-offline","title":"A Minimalist Approach to Offline Reinforcement Learning","date":"2021-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ba80f9ff81b1de5f","mcp_get_code":{"code_sha256":"ba80f9ff81b1de5f"}}]}