SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.12466 · NeurIPS · 2021

Information Directed Reward Learning for Reinforcement Learning

Andreas Krause, Kamil Ciosek, David Lindner, Matteo Turchetta, Sebastian Tschiatschek, Spotify

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 1 failure of our instrument; 0 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, measured 2026-11-21; 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/2102.12466.json · badge: /api/ran/2102.12466.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
david-lindner/idrl canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_entry_or_default Ran
ran; our contract draft was wrong, not the code
david-lindner/idrl/run_sacred_experiments.py
code served (permissive licence) · get_code("735f7ca6fa1635b8")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned str. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:24:16Z). 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 torch

torch.manual_seed(0)

# The function get_entry_or_default takes three parameters:
# 1. label: a key to look up
# 2. config: a dict-like object that supports __getitem__ and raises KeyError
# 3. default: a default value to return if the key is not found

# Test case 1: key exists in config
config_with_key = {
    "model_name": "bert-base",
    "learning_rate": 0.001,
    "batch_size": 32
}

# Test case 2: key does not exist, should return default
config_without_key = {
    "model_name": "bert-base"
}

# We'll use the case where the key exists
ARGS = {
    "label": "model_name",
    "config": config_with_key,
    "default": "gpt2"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
harmonic_number Ran
ran, honoured the contract we drafted
david-lindner/idrl/active_reward_learning/drlhp/drlhp.py
code served (permissive licence) · get_code("ddcd7cabe92eb030")
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) and returned float, ndim 0, dtype family float, 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 torch
import numpy as np

torch.manual_seed(0)

# The function harmonic_number takes a single parameter 'n'
# It converts n to int and computes the harmonic series sum
# We need to provide a valid numeric value for n

ARGS = {
    "n": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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 2026-11-21.

Repositories linked to this paper

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

Abstract

For many reinforcement learning (RL) applications, specifying a reward is difficult. This paper considers an RL setting where the agent obtains information about the reward only by querying an expert that can, for example, evaluate individual states or provide binary preferences over trajectories. From such expensive feedback, we aim to learn a model of the reward that allows standard RL algorithms to achieve high expected returns with as few expert queries as possible. To this end, we propose Information Directed Reward Learning (IDRL), which uses a Bayesian model of the reward and selects queries that maximize the information gain about the difference in return between plausibly optimal policies. In contrast to prior active reward learning methods designed for specific types of queries, IDRL naturally accommodates different query types. Moreover, it achieves similar or better performance with significantly fewer queries by shifting the focus from reducing the reward approximation error to improving the policy induced by the reward model. We support our findings with extensive evaluations in multiple environments and with different query types.

For agents

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

get_harvested_code_for_paper("2102.12466")
get_code_for_paper("2102.12466")
have("2102.12466")

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

curl https://syntology.ai/api/ran/2102.12466.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.12466.svg)](https://syntology.ai/paper/2102.12466)

Connect an agent — have() is free.