SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1804.04012 · 2018

DORA The Explorer: Directed Outreaching Reinforcement Action-Selection

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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 1 has no contract verdict; 0 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/1804.04012.json · badge: /api/ran/1804.04012.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
borgr/DORA canonical (classifier label)
classifier basis: census
1 ran · 2 no recorded run
FunctionStatusWhere it lives
tiles Ran
ran on a synthesized input
borgr/DORA/linapprox/tiles3.py
code served (permissive licence) · get_code("bf0c23acedec7379")
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 numpy as np
from math import floor

class IHT:
    """Structure to handle collisions"""

    def __init__(self, sizeval):
        self.size = sizeval
        self.overfullCount = 0
        self.dictionary = {}

    def __str__(self):
        """Prepares a string for printing whenever this object is printed"""
        return 'Collision table:' + ' size:' + str(self.size) + ' overfullCount:' + str(self.overfullCount) + ' dictionary:' + str(len(self.dictionary)) + ' items'

    def count(self):
        return len(self.dictionary)

    def fullp(self):
        return len(self.dictionary) >= self.size

    def getindex(self, obj, readonly=False):
        d = self.dictionary
        if obj in d:
            return d[obj]
        elif readonly:
            return None
        size = self.size
        count = self.count()
        if count >= size:
            if self.overfullCount == 0:
                print('IHT full, starting to allow collisions')
            self.overfullCount += 1
            return hash(obj) % self.size
        else:
            d[obj] = count
            return count


# Create test arguments for the tiles function
torch.manual_seed(0)
np.random.seed(0)

# ihtORsize: can be an IHT instance, an int, or None
iht_instance = IHT(256)

# numtilings: number of tilings to generate
numtilings = 4

# floats: list of float values to tile
floats = [0.1, 0.5, 0.7, 0.3]

# ints: optional list of integers to append to coordinates
ints = [1, 2]

# readonly: whether to use read-only mode
readonly = False

ARGS = {
    'ihtORsize': iht_instance,
    'numtilings': numtilings,
    'floats': floats,
    'ints': ints,
    'readonly': readonly
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
hashcoords Not yet run
unverified (harvested, no recorded run)
borgr/DORA/linapprox/tiles3.py
code served (permissive licence) · get_code("b407aa03e6b8a785")
How it ran

no invocation recorded.

tileswrap Not yet run
unverified (harvested, no recorded run)
borgr/DORA/linapprox/tiles3.py
code served (permissive licence) · get_code("2d3646df38ff4b06")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-action trajectories. We compare our approach to commonly used RL techniques, and show that using $E$-values improves learning and performance over traditional counters. We also show how our method can be implemented with function approximation to efficiently learn continuous MDPs. We demonstrate this by showing that our approach surpasses state of the art performance in the Freeway Atari 2600 game.

For agents

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

get_harvested_code_for_paper("1804.04012")
get_code_for_paper("1804.04012")
have("1804.04012")

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

curl https://syntology.ai/api/ran/1804.04012.json

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

[![Syntology run record](https://syntology.ai/api/ran/1804.04012.svg)](https://syntology.ai/paper/1804.04012)

Connect an agent — have() is free.