{"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/quantile-huber-loss","entry":"quantile_huber_loss","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":9,"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":7,"n_samples_ran":6,"n_samples_fingerprinted":2,"n_places":9,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"ran":4,"unverified":1},"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":"2603.17685","paper":"/paper/arxiv-2603-17685","title":"Flow Matching Policy Optimization with Mirror Descent and Entropy Constraints","date":"2026-03-18","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"wadx2019/qvpo","path":"agent/qvpo.py","file_url":"https://github.com/wadx2019/qvpo/blob/HEAD/agent/qvpo.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3e12dfe5d2e56c8d","mcp_get_code":{"code_sha256":"3e12dfe5d2e56c8d"}},{"arxiv_id":"2410.11022","paper":"/paper/action-gaps-and-advantages-in-continuous-time","title":"Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"harwiltz/distributional-superiority","path":"dsup/losses.py","file_url":"https://github.com/harwiltz/distributional-superiority/blob/HEAD/dsup/losses.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6323d3872e290271","mcp_get_code":{"code_sha256":"6323d3872e290271"}},{"arxiv_id":"2310.04373","paper":"/paper/confronting-reward-model-overoptimization","title":"Confronting Reward Model Overoptimization with Constrained RLHF","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tedmoskovitz/constrainedrl4lms","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/tedmoskovitz/constrainedrl4lms/blob/HEAD/rl4lms/algorithms/common/algo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"821b0061bc694ddf","mcp_get_code":{"code_sha256":"821b0061bc694ddf"}},{"arxiv_id":"2305.08844","paper":"/paper/rl4f-generating-natural-language-feedback","title":"RL4F: Generating Natural Language Feedback with Reinforcement Learning for Repairing Model Outputs","date":"2023-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/RL4LMs","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/allenai/RL4LMs/blob/HEAD/rl4lms/algorithms/common/algo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"821b0061bc694ddf","mcp_get_code":{"code_sha256":"821b0061bc694ddf"}},{"arxiv_id":"2302.11520","paper":"/paper/guiding-large-language-models-via-directional-1","title":"Guiding Large Language Models via Directional Stimulus Prompting","date":"2023-02-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"leezekun/directional-stimulus-prompting","path":"rl4lms/algorithms/common/algo_utils.py","file_url":"https://github.com/leezekun/directional-stimulus-prompting/blob/HEAD/rl4lms/algorithms/common/algo_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"821b0061bc694ddf","mcp_get_code":{"code_sha256":"821b0061bc694ddf"}},{"arxiv_id":"2212.00124","paper":"/paper/one-risk-to-rule-them-all-a-risk-sensitive-1","title":"One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning","date":"2022-11-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nuria95/O-RAAC","path":"oraaclib/agent/ORAAC.py","file_url":"https://github.com/nuria95/O-RAAC/blob/HEAD/oraaclib/agent/ORAAC.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":"24475939b27492ce","mcp_get_code":{"code_sha256":"24475939b27492ce"}},{"arxiv_id":"2211.15034","paper":"/paper/quantile-constrained-reinforcement-learning-a","title":"Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability","date":"2022-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wyjung0625/QCPO","path":"qcpo/dist_rl_utils.py","file_url":"https://github.com/wyjung0625/QCPO/blob/HEAD/qcpo/dist_rl_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c3eedd504cc05a91","mcp_get_code":{"code_sha256":"c3eedd504cc05a91"}},{"arxiv_id":"2006.14171","paper":"/paper/a-closer-look-at-invalid-action-masking-in","title":"A Closer Look at Invalid Action Masking in Policy Gradient Algorithms","date":"2020-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Stable-Baselines-Team/stable-baselines3-contrib","path":"sb3_contrib/common/utils.py","file_url":"https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/HEAD/sb3_contrib/common/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8a3b5a2760bcc10a","mcp_get_code":{"code_sha256":"8a3b5a2760bcc10a"}},{"arxiv_id":"1905.09638","paper":"/paper/estimating-risk-and-uncertainty-in-deep","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","date":"2019-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"IndustAI/risk-and-uncertainty","path":"figs2-3_rl/agents/common/utils.py","file_url":"https://github.com/IndustAI/risk-and-uncertainty/blob/HEAD/figs2-3_rl/agents/common/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a33e58b8c715af18","mcp_get_code":{"code_sha256":"a33e58b8c715af18"}}]}