SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.09809 · 2024

Preserving the Privacy of Reward Functions in MDPs through Deception

arXiv · PDF · Open in the Atlas

Code that ran

6 of 10 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.09809.json · badge: /api/ran/2407.09809.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
shshnkreddy/deceptiverl canonical (classifier label)
classifier basis: census
6 ran · 4 no recorded run
FunctionStatusWhere it lives
check_sol Ran
ran; our contract draft was wrong, not the code
shshnkreddy/deceptiverl/utils.py
pointer only (licence: NONE) · get_code("b763b6ab2bad7dc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

featurize Ran
ran, honoured the contract we drafted
shshnkreddy/deceptiverl/featurize.py
pointer only (licence: NONE) · get_code("b8e24ae762db8a5b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_pi Ran
ran; our contract draft was wrong, not the code
shshnkreddy/deceptiverl/utils.py
pointer only (licence: NONE) · get_code("0b69f062833f0edb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_v Ran
ran on a synthesized input
shshnkreddy/deceptiverl/utils.py
pointer only (licence: NONE) · get_code("1872cedf1821faf4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_seeds Ran
ran, honoured the contract we drafted
shshnkreddy/deceptiverl/util.py
pointer only (licence: NONE) · get_code("dfdfb59b3cffd4a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

squeeze_r Ran
ran; our contract draft was wrong, not the code
shshnkreddy/deceptiverl/mce_irl.py
pointer only (licence: NONE) · get_code("e82bc835365d6ee5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

closest_potential Not yet run
unverified (harvested, no recorded run)
shshnkreddy/deceptiverl/epic.py
pointer only (licence: NONE) · get_code("fde68a593d79622a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

closest_reward_am Not yet run
unverified (harvested, no recorded run)
shshnkreddy/deceptiverl/epic.py
pointer only (licence: NONE) · get_code("35006a189a255f8a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

oric Not yet run
unverified (harvested, no recorded run)
shshnkreddy/deceptiverl/util.py
pointer only (licence: NONE) · get_code("4ca4fdd8b8eca4ab")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

shape Not yet run
unverified (harvested, no recorded run)
shshnkreddy/deceptiverl/epic.py
pointer only (licence: NONE) · get_code("8bf23ee16d057358")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, shshnkreddy/deceptiverl when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 0 later) and 7 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
closest_potential 1 other paper
1 dated earlier
2006.13900 (2020-06)
Quantifying Differences in Reward Functions
shape 1 other paper
1 dated earlier
2006.13900 (2020-06)
Quantifying Differences in Reward Functions
squeeze_r 1 other paper
1 dated earlier
2211.11972 (2022-11)
imitation: Clean Imitation Learning Implementations

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, agents must allocate patrolling resources without revealing animal locations to poachers. This paper addresses privacy preservation in planning over a sequence of actions in MDPs, where the reward function represents the preference structure to be protected. Observers can use Inverse RL (IRL) to learn these preferences, making this a challenging task. Current research on differential privacy in reward functions fails to ensure guarantee on the minimum expected reward and offers theoretical guarantees that are inadequate against IRL-based observers. To bridge this gap, we propose a novel approach rooted in the theory of deception. Deception includes two models: dissimulation (hiding the truth) and simulation (showing the wrong). Our first contribution theoretically demonstrates significant privacy leaks in existing dissimulation-based methods. Our second contribution is a novel RL-based planning algorithm that uses simulation to effectively address these privacy concerns while ensuring a guarantee on the expected reward. Experiments on multiple benchmark problems show that our approach outperforms previous methods in preserving reward function privacy.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.09809")
get_code_for_paper("2407.09809")
have("2407.09809")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.09809.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.09809.svg)](https://syntology.ai/paper/2407.09809)

Connect an agent — have() is free.