Papers › Learning Optimal Advantage from Preferences and Mistaking it for Reward

Learning Optimal Advantage from Preferences and Mistaking it for Reward

3 Oct 2023arXiv:2310.02456archive 2025-07-28

W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur Orn Adalgeirsson, Serena Booth, Anca Dragan, Peter Stone, Scott Niekum

We consider algorithms for learning reward functions from human preferences over pairs of trajectory segments, as used in reinforcement learning from human feedback (RLHF). Most recent work assumes that human preferences are generated based only upon the reward accrued within those segments, or their partial return. Recent work casts doubt on the validity of this assumption, proposing an alternative preference model based upon regret. We investigate the consequences of assuming preferences are based upon partial return when they actually arise from regret. We argue that the learned function is an approximation of the optimal advantage function, Â^̂*̂ᵣ̂, not a reward function. We find that if a specific pitfall is addressed, this incorrect assumption is not particularly harmful, resulting in a highly shaped reward function. Nonetheless, this incorrect usage of Â^̂*̂ᵣ̂ is less desirable than the appropriate and simpler approach of greedy maximization of Â^̂*̂ᵣ̂. From the perspective of the regret preference model, we also provide a clearer interpretation of fine tuning contemporary large language models with RLHF. This paper overall provides insight regarding why learning under the partial return preference model tends to work so well in practice, despite it conforming poorly to how humans give preferences.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

Stephanehk/Learning-OA-From-Prefs officialmentioned in paperpytorchSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

11ran
1unverified

Licence: 12 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Stephanehk/Learning-OA-From-Prefs. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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 label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

Stephanehk/Learning-OA-From-Prefs official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
build_pi_from_nn_feats learn_advantage/algorithms/rl_algos.py ran no licence file found · pointer only · f6e5bcc0d13ef9a6 · report fixture: signature model:callable/0/?, env:GridWorldEnv/0/? · returned dict · level recorded 2026-09-24
build_reward_from_nn_feats learn_advantage/algorithms/rl_algos.py ran no licence file found · pointer only · 7739f17cbdd84716 · report fixture: signature model:callable/0/?, env:MockEnv/0/? · returned ndarray · level recorded 2026-09-24
find_end_state learn_advantage/env/generate_random_mdp.py ran no licence file found · pointer only · 1d126d83c8e0f620 · report fixture: signature traj:list/1/list, board:list/1/list · returned tuple · level recorded 2026-09-24
get_loops in 8 papers learn_advantage/analysis/generate_fig_5.py ran no licence file found · pointer only · e3448e1f08ace362 · report fixture: signature start_x:int/0/int, stary_y:int/0/int, oaf:ndarray/3/float, env:SimpleEnv/0/? · returned list · level recorded 2026-09-24
get_random_reward_vector learn_advantage/env/generate_random_policies.py ran no licence file found · pointer only · 45d3e57f998c2581 · report fixture: signature gt_rew_vec:NoneType/0/? · returned ndarray · level recorded 2026-09-24
get_reward_vec learn_advantage/algorithms/advantage_learning.py ran no licence file found · pointer only · 7830dff13490ae72 · report fixture: signature args:Args/0/?, model:callable/0/? · returned ndarray · level recorded 2026-09-24
is_arr_in_list learn_advantage/env/generate_random_policies.py ran no licence file found · pointer only · 0428bfbecb501b40 · report fixture: signature myarr:ndarray/1/int, list_arrays:list/1/ndarray · returned bool · level recorded 2026-09-24
is_in_blocked_area learn_advantage/env/generate_random_mdp.py ran no licence file found · pointer only · f8de7019770bfdbe · report fixture: signature x:int/0/int, y:int/0/int, board:list/1/list · returned bool · level recorded 2026-09-24
is_in_gated_area learn_advantage/env/generate_random_mdp.py ran no licence file found · pointer only · dcf3a8b47b339ebf · report fixture: signature x:int/0/int, y:int/0/int, board:list/1/list · returned bool · level recorded 2026-09-24
reward_pred_loss learn_advantage/algorithms/advantage_learning.py ran no licence file found · pointer only · 9b36c07728845fbc · report fixture: signature output:Tensor/2/float, target:Tensor/1/float · returned Tensor · level recorded 2026-09-24
run_single_set learn_advantage/algorithms/advantage_learning.py ran no licence file found · pointer only · dd91e5da29ece6a8 · report fixture: signature model:callable/0/?, optimizer:Adam/0/?, X_train:Tensor/2/float, y_train:Tensor/2/float · returned tuple · level recorded 2026-09-24
parse_args in 355 papers learn_advantage/utils/argparse_utils.py unverified no licence file found · pointer only · 2708f9e87af72605 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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