{"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/expectile-loss","entry":"expectile_loss","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":13,"n_papers_ran":11,"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":7,"n_samples_fingerprinted":6,"n_places":15,"n_places_pointer_only":11,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":5,"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":"2608.07870","paper":"/paper/arxiv-2608-07870","title":"V-Simba: Unleashing the Architectural Potential of RL in Visual Continuous Control","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"FrankZheng2022/TACO","path":"utils.py","file_url":"https://github.com/FrankZheng2022/TACO/blob/HEAD/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":"f55fa75eaa288304","mcp_get_code":{"code_sha256":"f55fa75eaa288304"}},{"arxiv_id":"2511.02567","paper":"/paper/arxiv-2511-02567","title":"Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2025-11","title_source":"syntology","repo":"thu-rllab/ANQ","path":"ANQ.py","file_url":"https://github.com/thu-rllab/ANQ/blob/HEAD/ANQ.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"aeac8b96e388243c","mcp_get_code":{"code_sha256":"aeac8b96e388243c"}},{"arxiv_id":"2502.05932","paper":"/paper/skill-expansion-and-composition-in-parameter","title":"Skill Expansion and Composition in Parameter Space","date":"2025-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ltlhuuu/PSEC","path":"jaxrl5/agents/psec/psec_finetune.py","file_url":"https://github.com/ltlhuuu/PSEC/blob/HEAD/jaxrl5/agents/psec/psec_finetune.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ad221b0896e1bcd0","mcp_get_code":{"code_sha256":"ad221b0896e1bcd0"}},{"arxiv_id":"2412.07762","paper":"/paper/efficient-online-reinforcement-learning-fine","title":"Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data","date":"2024-12-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhouzypaul/wsrl","path":"wsrl/agents/iql.py","file_url":"https://github.com/zhouzypaul/wsrl/blob/HEAD/wsrl/agents/iql.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7d4237621248f7f9","mcp_get_code":{"code_sha256":"7d4237621248f7f9"}},{"arxiv_id":"2411.07934","paper":"/paper/doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maoyixiu/dmg","path":"DMG.py","file_url":"https://github.com/maoyixiu/dmg/blob/HEAD/DMG.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":"9142ce9e4598b83a","mcp_get_code":{"code_sha256":"9142ce9e4598b83a"}},{"arxiv_id":"2411.07934","paper":"/paper/doubly-mild-generalization-for-offline","title":"Doubly Mild Generalization for Offline Reinforcement Learning","date":"2024-11-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"maoyixiu/dmg","path":"DMG.py","file_url":"https://github.com/maoyixiu/dmg/blob/HEAD/DMG.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c275742f36ec65ee","mcp_get_code":{"code_sha256":"c275742f36ec65ee"}},{"arxiv_id":"2402.17135","paper":"/paper/unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kvfrans/fre","path":"algs/iql.py","file_url":"https://github.com/kvfrans/fre/blob/HEAD/algs/iql.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad221b0896e1bcd0","mcp_get_code":{"code_sha256":"ad221b0896e1bcd0"}},{"arxiv_id":"2402.17135","paper":"/paper/unsupervised-zero-shot-reinforcement-learning","title":"Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kvfrans/fre","path":"experiment/run_fre.py","file_url":"https://github.com/kvfrans/fre/blob/HEAD/experiment/run_fre.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"33d24c59c871db71","mcp_get_code":{"code_sha256":"33d24c59c871db71"}},{"arxiv_id":"2402.06187","paper":"/paper/premier-taco-pretraining-multitask","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","date":"2024-02-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"PremierTACO/premier-taco","path":"utils.py","file_url":"https://github.com/PremierTACO/premier-taco/blob/HEAD/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":"f55fa75eaa288304","mcp_get_code":{"code_sha256":"f55fa75eaa288304"}},{"arxiv_id":"2401.10700","paper":"/paper/safe-offline-reinforcement-learning-with","title":"Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model","date":"2024-01-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ZhengYinan-AIR/FISOR","path":"jaxrl5/agents/fisor/fisor.py","file_url":"https://github.com/ZhengYinan-AIR/FISOR/blob/HEAD/jaxrl5/agents/fisor/fisor.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ad221b0896e1bcd0","mcp_get_code":{"code_sha256":"ad221b0896e1bcd0"}},{"arxiv_id":"2307.11949","paper":"/paper/hiql-offline-goal-conditioned-rl-with-latent-1","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","date":"2023-07-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seohongpark/hiql","path":"src/agents/hiql.py","file_url":"https://github.com/seohongpark/hiql/blob/HEAD/src/agents/hiql.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"33d24c59c871db71","mcp_get_code":{"code_sha256":"33d24c59c871db71"}},{"arxiv_id":"2304.10573","paper":"/paper/idql-implicit-q-learning-as-an-actor-critic","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","date":"2023-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"code_sha256_prefix":"ad221b0896e1bcd0","mcp_get_code":{"code_sha256":"ad221b0896e1bcd0"}},{"arxiv_id":"2304.04782","paper":"/paper/reinforcement-learning-from-passive-data-via","title":"Reinforcement Learning from Passive Data via Latent Intentions","date":"2023-04-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dibyaghosh/icvf_release","path":"src/icvf_learner.py","file_url":"https://github.com/dibyaghosh/icvf_release/blob/HEAD/src/icvf_learner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"97edc824282c1fed","mcp_get_code":{"code_sha256":"97edc824282c1fed"}},{"arxiv_id":"2302.00935","paper":"/paper/policy-expansion-for-bridging-offline-to","title":"Policy Expansion for Bridging Offline-to-Online Reinforcement Learning","date":"2023-02-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"haichao-zhang/pex","path":"pex/algorithms/pex.py","file_url":"https://github.com/haichao-zhang/pex/blob/HEAD/pex/algorithms/pex.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d62277986ed1bdb1","mcp_get_code":{"code_sha256":"d62277986ed1bdb1"}},{"arxiv_id":"2110.06169","paper":"/paper/offline-reinforcement-learning-with-implicit","title":"Offline Reinforcement Learning with Implicit Q-Learning","date":"2021-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"orrivlin/implicit-q-learning","path":"IQL.py","file_url":"https://github.com/orrivlin/implicit-q-learning/blob/HEAD/IQL.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":"f55fa75eaa288304","mcp_get_code":{"code_sha256":"f55fa75eaa288304"}}]}