SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.02439 · NeurIPS · 2021

Replay-Guided Adversarial Environment Design

Jack Parker-Holder, Jakob Foerster, Michael Dennis, Minqi Jiang

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 3 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/2110.02439.json · badge: /api/ran/2110.02439.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
facebookresearch/minimax community
Papers with Code archive
1 ran · 2 no recorded run
fictivename/dcd_mujoco community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
PLRBuffer Ran
ran on a synthesized input · constructed an object; no result was computed
facebookresearch/minimax/src/minimax/util/rl/plr.py
code served (permissive licence) · get_code("0ddca4701961c4c7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned an instance of its own class, PLRBuffer: the run constructed the object and did not call it, so no result was computed. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
import jax
import jax.numpy as jnp
from flax import struct
import chex

class UEDScore:
    RELATIVE_REGRET = 1
    MEAN_RELATIVE_REGRET = 2
    POPULATION_REGRET = 3
    RETURN = 4
    NEG_RETURN = 5
    L1_VALUE_LOSS = 6
    POSITIVE_VALUE_LOSS = 7
    MAX_MC = 8
    VALUE_DISAGREEMENT = 9

buffer_size = 100

ARGS = {
    "levels": jnp.zeros((buffer_size,), dtype=jnp.float32),
    "scores": jnp.zeros((buffer_size,), dtype=jnp.float32),
    "ages": jnp.zeros((buffer_size,), dtype=jnp.int32),
    "max_returns": jnp.zeros((buffer_size,), dtype=jnp.float32),
    "filled": jnp.zeros((buffer_size,), dtype=jnp.bool_),
    "filled_count": jnp.array(0, dtype=jnp.int32),
    "n_mutations": jnp.zeros((buffer_size,), dtype=jnp.int32),
    "ued_score": UEDScore.L1_VALUE_LOSS,
    "replay_prob": 0.5,
    "buffer_size": 100,
    "staleness_coef": 0.3,
    "temp": 1.0,
    "use_score_ranks": True,
    "min_fill_ratio": 0.5,
    "use_robust_plr": False,
    "use_parallel_eval": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
chex, flax, jax, numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type PLRBuffer — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a PLRBuffer output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
LevelSampler Not yet run
unverified (harvested, no recorded run)
fictivename/dcd_mujoco/level_replay/level_sampler.py
pointer only (licence: NOASSERTION) · get_code("92c4db04a096b3db")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, fictivename/dcd_mujoco (NOASSERTION). 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.

PLRManager Not yet run
unverified (harvested, no recorded run)
facebookresearch/minimax/src/minimax/util/rl/plr.py
code served (permissive licence) · get_code("da77c74235c8a34e")
How it ran

no invocation recorded.

UEDScore Not yet run
unverified (harvested, no recorded run)
facebookresearch/minimax/src/minimax/util/rl/plr.py
code served (permissive licence) · get_code("0646e27a0ec531fa")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Deep reinforcement learning (RL) agents may successfully generalize to new settings if trained on an appropriately diverse set of environment and task configurations. Unsupervised Environment Design (UED) is a promising selfsupervised RL paradigm, wherein the free parameters of an underspecified environment are automatically adapted during training to the agent's capabilities, leading to the emergence of diverse training environments. Here, we cast Prioritized Level Replay (PLR), an empirically successful but theoretically unmotivated method that selectively samples randomly-generated training levels, as UED. We argue that by curating completely random levels, PLR, too, can generate novel and complex levels for effective training. This insight reveals a natural class of UED methods we call Dual Curriculum Design (DCD). Crucially, DCD includes both PLR and a popular UED algorithm, PAIRED, as special cases and inherits similar theoretical guarantees. This connection allows us to develop novel theory for PLR, providing a version with a robustness guarantee at Nash equilibria. Furthermore, our theory suggests a highly counterintuitive improvement to PLR: by stopping the agent from updating its policy on uncurated levels (training on less data), we can improve the convergence to Nash equilibria. Indeed, our experiments confirm that our new method, PLR ⊥ , obtains better results on a suite of out-of-distribution, zero-shot transfer tasks, in addition to demonstrating that PLR ⊥ improves the performance of PAIRED, from which it inherited its theoretical framework.

For agents

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

get_harvested_code_for_paper("2110.02439")
get_code_for_paper("2110.02439")
have("2110.02439")

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

curl https://syntology.ai/api/ran/2110.02439.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.02439.svg)](https://syntology.ai/paper/2110.02439)

Connect an agent — have() is free.