SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10228 · 2024

Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 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/2402.10228.json · badge: /api/ran/2402.10228.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
szrlee/hyperagent canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
make_env Ran
ran; our contract draft was wrong, not the code
szrlee/hyperagent/hyperagent/env/utils.py
code served (permissive licence) · get_code("7987a0deae85f58b")
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 TimeLimit. 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 gym

ARGS = {
    "env_name": "CartPole-v1",
    "max_step": 500,
    "env_config": {}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
gym — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type TimeLimit — a TimeLimit output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a TimeLimit 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
miniblock Ran
ran; our contract draft was wrong, not the code
szrlee/hyperagent/hyperagent/network/common.py
code served (permissive licence) · get_code("ced646fc0c60b73a")
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 list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    "input_size": 4,
    "output_size": 3,
    "norm_layer": nn.BatchNorm1d,
    "activation": nn.ReLU,
    "linear_layer": nn.Linear
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
rd_argmax Ran
ran, honoured the contract we drafted
szrlee/hyperagent/hyperagent/policy/hyper_utils.py
code served (permissive licence) · get_code("6d1e49fae9c78bff")
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 int64, ndim 0, dtype family int, shape () as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape 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

# Set random seed for reproducibility
np.random.seed(0)

# Create a simple vector with some maximum values
# The function finds the maximum value and randomly selects among indices with that max value
vector = np.array([1.0, 5.0, 3.0, 5.0, 2.0])

ARGS = {
    "vector": vector
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int64, ndim 0, dtype family int, shape () — shape () as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
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
make_atari_env Not yet run
unverified (harvested, no recorded run)
szrlee/hyperagent/hyperagent/env/utils.py
code served (permissive licence) · get_code("cedd0815975bd1b5")
How it ran

no invocation recorded.

make_atari_env_watch Not yet run
unverified (harvested, no recorded run)
szrlee/hyperagent/hyperagent/env/utils.py
code served (permissive licence) · get_code("06b74e86dd4dc4da")
How it ran

no invocation recorded.

wrap_atari Not yet run
unverified (harvested, no recorded run)
szrlee/hyperagent/hyperagent/env/atari_wrapper.py
code served (permissive licence) · get_code("ebe5258db5d557d3")
How it ran

no invocation recorded.

wrap_deepmind Not yet run
unverified (harvested, no recorded run)
szrlee/hyperagent/hyperagent/env/atari_wrapper.py
code served (permissive licence) · get_code("f407a5134f319b52")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 5 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
miniblock 2 other papers
2 dated earlier
2307.08290 (2023-07)
CoAD: Automatic Diagnosis through Symptom and Disease Collaborative Generation
2309.03208 (2023-09)
A Circuit Domain Generalization Framework for Efficient Logic Synthesis in Chip Design
wrap_deepmind 1 other paper
1 dated earlier
2205.10868 (2022-05)
Memory-efficient Reinforcement Learning with Value-based Knowledge Consolidation

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

We propose HyperAgent, a reinforcement learning (RL) algorithm based on the hypermodel framework for exploration in RL. HyperAgent allows for the efficient incremental approximation of posteriors associated with an optimal action-value function ($Q^\star$) without the need for conjugacy and follows the greedy policies w.r.t. these approximate posterior samples. We demonstrate that HyperAgent offers robust performance in large-scale deep RL benchmarks. It can solve Deep Sea hard exploration problems with episodes that optimally scale with problem size and exhibits significant efficiency gains in the Atari suite. Implementing HyperAgent requires minimal code addition to well-established deep RL frameworks like DQN. We theoretically prove that, under tabular assumptions, HyperAgent achieves logarithmic per-step computational complexity while attaining sublinear regret, matching the best known randomized tabular RL algorithm.

For agents

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

get_harvested_code_for_paper("2402.10228")
get_code_for_paper("2402.10228")
have("2402.10228")

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

curl https://syntology.ai/api/ran/2402.10228.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10228.svg)](https://syntology.ai/paper/2402.10228)

Connect an agent — have() is free.