SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.12284 · ICML · 2024

Refining Minimax Regret for Unsupervised Environment Design

Jakob Foerster, Michael Dennis, Minqi Jiang, Mattie Fellows, Michael Beukman, Samuel Coward, Michael Matthews, Michael Beuk

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 6 failures of our instrument; 2 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/2402.12284.json · badge: /api/ran/2402.12284.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
michael-beukman/remidi canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_gae Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/common/ppo.py
pointer only (licence: NONE) · get_code("f20aa0108a055874")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

fill_coords Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/environments/maze/vis.py
pointer only (licence: NONE) · get_code("807cd87fb87d6b5d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

load_compressed_pickle Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/utils.py
pointer only (licence: NONE) · get_code("a0fcd1a9937f59d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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_lever_level_generator Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/environments/lever_game/env.py
pointer only (licence: NONE) · get_code("2738cb883a4907b2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

point_in_rect Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/environments/maze/vis.py
pointer only (licence: NONE) · get_code("27e5ee93023a1020")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

point_in_triangle Ran
ran; our contract draft was wrong, not the code
michael-beukman/remidi/lib/environments/maze/vis.py
pointer only (licence: NONE) · get_code("680139aaead3ac7d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

sample_trajectories_rnn Not yet run
unverified (harvested, no recorded run)
michael-beukman/remidi/lib/common/ppo.py
pointer only (licence: NONE) · get_code("b51283140c732791")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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.

update_actor_critic_rnn Not yet run
unverified (harvested, no recorded run)
michael-beukman/remidi/lib/common/ppo.py
pointer only (licence: NONE) · get_code("0b73880de813328a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, michael-beukman/remidi 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 8 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

In unsupervised environment design, reinforcement learning agents are trained on environment configurations (levels) generated by an adversary that maximises some objective. Regret is a commonly used objective that theoretically results in a minimax regret (MMR) policy with desirable robustness guarantees; in particular, the agent's maximum regret is bounded. However, once the agent reaches this regret bound on all levels, the adversary will only sample levels where regret cannot be further reduced. Although there may be possible performance improvements to be made outside of these regret-maximising levels, learning stagnates. In this work, we introduce Bayesian level-perfect MMR (BLP), a refinement of the minimax regret objective that overcomes this limitation. We formally show that solving for this objective results in a subset of MMR policies, and that BLP policies act consistently with a Perfect Bayesian policy over all levels. We further introduce an algorithm, ReMiDi, that results in a BLP policy at convergence. We empirically demonstrate that training on levels from a minimax regret adversary causes learning to prematurely stagnate, but that ReMiDi continues learning.

For agents

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

get_harvested_code_for_paper("2402.12284")
get_code_for_paper("2402.12284")
have("2402.12284")

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

curl https://syntology.ai/api/ran/2402.12284.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.12284.svg)](https://syntology.ai/paper/2402.12284)

Connect an agent — have() is free.