SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2607.29617 · 2026

When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning

Luca Viano, Philip Amortila, Antoine Moulin

arXiv · PDF

Code that ran

13 of 17 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; 3 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 9 failures of our instrument; 4 no recorded run), measured 2026-11-22; 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/2607.29617.json · badge: /api/ran/2607.29617.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
lviano/ovi canonical (classifier label)
classifier basis: census
13 ran · 4 no recorded run
FunctionStatusWhere it lives
build_tex Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/make_latex_scaling_plot.py
pointer only (licence: NONE) · get_code("9290845bcec04a3a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

expert_exists Ran
ran, violated the contract we drafted
lviano/ovi/gym_code/expert.py
pointer only (licence: NONE) · get_code("b4a03e55015a1728")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_env_config Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/env_configs.py
pointer only (licence: NONE) · get_code("897521428c446a2c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_size_stats Ran
ran, honoured the contract we drafted
lviano/ovi/gym_code/make_latex_scaling_plot.py
pointer only (licence: NONE) · get_code("c56e43305dae199b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

group_label Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/replot.py
pointer only (licence: NONE) · get_code("aa83b526cd67ba40")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_config_key Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/run_pendulum_experiment.py
pointer only (licence: NONE) · get_code("c219d99bd912231a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_config_key Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/run_traj_experiment.py
pointer only (licence: NONE) · get_code("8daf5567d229b1ec")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_env Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/run_traj_experiment.py
pointer only (licence: NONE) · get_code("4e536803a3f0eeb0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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_full_key Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/replot.py
pointer only (licence: NONE) · get_code("7936a9e443be02a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

parse_sa_key Ran
ran; our contract draft was wrong, not the code
lviano/ovi/gym_code/replot.py
pointer only (licence: NONE) · get_code("09124bc5c87ca353")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

q_dot_pi Ran
ran, honoured the contract we drafted
lviano/ovi/hard_mdp_experiment/algorithms.py
pointer only (licence: NONE) · get_code("2814ad590b82bbc6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

select_best_q Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
lviano/ovi/hard_mdp_experiment/algorithms.py
pointer only (licence: NONE) · get_code("f1eadacfea395f15")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

softmax_update Ran
ran, honoured the contract we drafted
lviano/ovi/hard_mdp_experiment/algorithms.py
pointer only (licence: NONE) · get_code("e411784694469adf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

build_tex Not yet run
unverified (harvested, no recorded run)
lviano/ovi/gym_code/make_latex_figure.py
pointer only (licence: NONE) · get_code("7c54d121572c3b10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

load_data Not yet run
unverified (harvested, no recorded run)
lviano/ovi/gym_code/make_latex_figure.py
pointer only (licence: NONE) · get_code("9d8024f7f19aafc7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

load_data Not yet run
unverified (harvested, no recorded run)
lviano/ovi/gym_code/make_latex_scaling_plot.py
pointer only (licence: NONE) · get_code("ecda781e53d76bad")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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.

measure_mean_traj_len Not yet run
unverified (harvested, no recorded run)
lviano/ovi/gym_code/run_traj_experiment.py
pointer only (licence: NONE) · get_code("33d7901e94f408e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lviano/ovi 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 16 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 16 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.

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

Imitation learning (IL)-training an agent to replicate expert behavior from demonstrations-underpins applications from robotics to language model training. Standard approaches such as Behavior Cloning (BC) are known to suffer from compounding errors and performance plateaus, particularly when the learner cannot perfectly represent the expert's policy (as is typical, e.g., in distillation). Two interventions are widely understood empirically to improve performance: querying the expert interactively along the learner's own trajectories, and using value function estimation en route to generating a policy rather than directly fitting the expert's full action distribution. We investigate the nature of these improvements and their potentially surprising interplay. Our main finding is that expert interaction relaxes the representational demands on the learner: one only needs a model capable of realizing the expert's value function, bypassing the (often stricter) requirement of realizing the expert's policy itself. Concretely, we introduce OVI, an interactive on-policy IL algorithm that is statistically efficient whenever the learner can represent the expert's value function and computationally efficient given access to a linear maximization oracle. We complement this with a negative result showing that interaction is necessary. Namely, without stronger assumptions beyond expert-value realizability alone, any offline IL algorithm must scale with the complexity of the expert policy class. Our findings bear out empirically. OVI outperforms offline policy-based (BC), interactive policy-based (DAgger), and offline value-based IL methods, with the largest gains when the learner network is substantially less expressive than the expert's. * Equal contribution.

For agents

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

get_harvested_code_for_paper("2607.29617")
get_code_for_paper("2607.29617")
have("2607.29617")

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

curl https://syntology.ai/api/ran/2607.29617.json

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

[![Syntology run record](https://syntology.ai/api/ran/2607.29617.svg)](https://syntology.ai/paper/2607.29617)

Connect an agent — have() is free.