Home › Code › RewardModel

RewardModel

Syntologyentry name in harvested coderead from the graph 2026-09-24

RewardModel appears in the code Syntology harvested for 10 papers, as 10 distinct code bodies found in 10 places (a place is one code body under one paper). At least one of them ran in 7 of the papers; 1 of the code bodies carries a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named RewardModel do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 7 of the 10 distinct code bodies named RewardModel; 3 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
0ran · our draft was wrong
0ran · fixture could not drive it
7ran
3unverified
1fingerprinted

Licence is a property of each copy, so it is counted per place: 5 of the 10 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

10 papers shown of 10, newest first; 10 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 2 papers added by Syntology. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's code_sha256, Syntology's identity for that exact code: an agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

PaperDateFileStatus SyntologyLicence
ArenaRL: Scaling RL for Open-Ended Agents via Tournamentbased Relative Ranking added by Syntology 2026-01 (from id) Alibaba-NLP/qqr/qqr/reward_models/arena/double_elimination.py 859b40ac082593cf unverified Apache-2.0 (permissive)
STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning added by Syntology 2025-09 (from id) iiiiii11/STAIR/reward_model.py 9b0f89e1331a5019 unverified no licence file found · pointer only
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries 31 May 2025 moonoutcloudback/clarify_pbrl/reward_model.py 3d27511acaa0b08b ran no licence file found · pointer only
Listwise Reward Estimation for Offline Preference-based Reinforcement Learning 8 Aug 2024 chwoong/lire/Reward_learning/reward_model.py 84a651a8f7389135 ran no licence file found · pointer only
RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences 27 Feb 2024 cjreinforce/rime_icml2024/reward_model_RIME.py 3a1138fef2b4ce3c unverified MIT (permissive)
Preference-grounded Token-level Guidance for Language Model Fine-tuning 1 Jun 2023 shentao-yang/preference_grounded_guidance/sum_task/reward_model.py 6fdf28a6230ef77d ran · metamorphic tier: deterministic no licence file found · pointer only
Query-Policy Misalignment in Preference-Based Reinforcement Learning 27 May 2023 huxiao09/qpa/reward_model.py fe29d8cf8d1bbbeb ran MIT (permissive)
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning 24 May 2022 rll-research/rune/reward_model_explore.py b518ac768ca194c9 ran fingerprinted MIT (permissive)
PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training 9 Jun 2021 pokaxpoka/b_pref/reward_model.py 7317e4f9684221bb ran no licence file found · pointer only
Dream to Control: Learning Behaviors by Latent Imagination 3 Dec 2019 Yizhao111/dreamer-pytorch/agent.py ff12acbebe54d7cc ran MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the harvest. "Pointer only" means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections