SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2202.12180 · 2022

Quantum Deep Reinforcement Learning for Robot Navigation Tasks

arXiv · PDF · Open in the Atlas

Code that ran

5 of 9 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 5 have no contract verdict; 0 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/2202.12180.json · badge: /api/ran/2202.12180.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
dfki-ric-quantum/qdrl-turtlebot-eval canonical (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
dfki-ric-quantum/qdrl-turtlebot-env canonical (classifier label)
classifier basis not recorded on the link
0 ran · 3 no recorded run
FunctionStatusWhere it lives
get_new_param Ran
ran on a synthesized input
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/quantum_circuit.py
code served (permissive licence) · get_code("7c816ef705de7628")
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 Symbol. 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 sympy

def get_new_param(symbol_name, qubit, position, layer=None):
    """
    return new learnable parameter
    """
    if str(layer):
        new_param = sympy.symbols(symbol_name + '_' + str(qubit) + '_' + str(layer) + '_' + str(position))
    else:
        new_param = sympy.symbols(symbol_name + '_' + str(qubit) + '_' + str(position))
    return new_param


ARGS = {
    "symbol_name": "theta",
    "qubit": 0,
    "position": 1,
    "layer": 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
sympy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Symbol — a Symbol output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Symbol 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
process_reward Ran
ran on a synthesized input
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/frozenlake.py
code served (permissive licence) · get_code("3a4f8ceb50bb75ab")
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 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

torch.manual_seed(0)

ARGS = {
    "reward": 0.5,
    "done": False
}
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 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
save_results Ran
ran on a synthesized input
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/utils.py
code served (permissive licence) · get_code("20234be6a42360b2")
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 str. 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 torch
import pickle
from datetime import datetime
from unittest.mock import MagicMock

torch.manual_seed(0)

# Create a minimal config class with __dict__ attribute
class Config:
    def __init__(self):
        self.learning_rate = 0.001
        self.batch_size = 32
        self.epochs = 10
        self.model_type = "transformer"

# Create a minimal args object with required attributes
class Args:
    def __init__(self):
        self.dir = "/tmp"
        self.config = "experiment"

# Create sample data
n = 5
args = Args()
config = Config()
rewards = [0.1, 0.2, 0.15, 0.25, 0.3, 0.28]

ARGS = {
    'n': n,
    'args': args,
    'config': config,
    'rewards': rewards
}
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 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
to_binary Ran
ran on a synthesized input
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/frozenlake.py
code served (permissive licence) · get_code("3402dfd16d7cdaca")
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 ndarray, ndim 1, dtype family float, shape (4,) 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 math
import numpy as np

# The function to_binary takes two parameters:
# - state: an integer representing which state
# - n_states: the total number of states

# Based on the function body:
# - state is used in bin(state) so it should be an integer
# - n_states is used in math.log(n_states, 2) so it should be a positive integer > 1
# - The function computes the number of binary digits needed and converts state to binary

ARGS = {
    "state": 5,
    "n_states": 16
}
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 ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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
to_tuple Ran
ran on a synthesized input
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/quantum_circuit.py
code served (permissive licence) · get_code("5819d9fdcbfeb812")
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 tuple. 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 torch
import numpy as np

torch.manual_seed(0)

# The function to_tuple recursively converts iterables to tuples
# It attempts to iterate over the input, and if that fails (TypeError),
# it returns the input as-is
# So we need to test it with various nested structures

# Test case 1: Simple nested list
nested_list = [1, [2, 3], [[4, 5], 6]]

# Test case 2: Mixed structures with tensors
nested_mixed = [
    torch.tensor([1.0, 2.0]),
    [3, 4],
    [[5, 6], torch.tensor([7.0, 8.0])]
]

# Test case 3: Deeply nested structure
deeply_nested = [[[[[1, 2], 3], 4], 5], 6]

# Test case 4: Simple scalar (should just return it)
scalar = 42

# Test case 5: Mix of lists, tuples, and numpy arrays
mixed_containers = [
    np.array([1, 2, 3]),
    [torch.tensor([4.0, 5.0]), 6],
    7
]

# Use the first test case as the main argument
a = nested_list

ARGS = {
    "a": a
}
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 tuple — a tuple output has no array shape of its own; none is 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
compute_avg_reward Not yet run
unverified (harvested, no recorded run)
dfki-ric-quantum/qdrl-turtlebot-eval/qeval/runner.py
code served (permissive licence) · get_code("622209d3d7626703")
How it ran

no invocation recorded.

default_builder Not yet run
unverified (harvested, no recorded run)
dfki-ric-quantum/qdrl-turtlebot-env/qturtle/builders/default.py
code served (permissive licence) · get_code("8c3cf11a69877944")
How it ran

no invocation recorded.

lidar_env_builder Not yet run
unverified (harvested, no recorded run)
dfki-ric-quantum/qdrl-turtlebot-env/qturtle/builders/default.py
code served (permissive licence) · get_code("9ac0dddb3211bc21")
How it ran

no invocation recorded.

make Not yet run
unverified (harvested, no recorded run)
dfki-ric-quantum/qdrl-turtlebot-env/qturtle/core.py
code served (permissive licence) · get_code("c54986e5c79ff74d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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

We utilize hybrid quantum deep reinforcement learning to learn navigation tasks for a simple, wheeled robot in simulated environments of increasing complexity. For this, we train parameterized quantum circuits (PQCs) with two different encoding strategies in a hybrid quantum-classical setup as well as a classical neural network baseline with the double deep Q network (DDQN) reinforcement learning algorithm. Quantum deep reinforcement learning (QDRL) has previously been studied in several relatively simple benchmark environments, mainly from the OpenAI gym suite. However, scaling behavior and applicability of QDRL to more demanding tasks closer to real-world problems e. g., from the robotics domain, have not been studied previously. Here, we show that quantum circuits in hybrid quantum-classic reinforcement learning setups are capable of learning optimal policies in multiple robotic navigation scenarios with notably fewer trainable parameters compared to a classical baseline. Across a large number of experimental configurations, we find that the employed quantum circuits outperform the classical neural network baselines when equating for the number of trainable parameters. Yet, the classical neural network consistently showed better results concerning training times and stability, with at least one order of magnitude of trainable parameters more than the best-performing quantum circuits. However, validating the robustness of the learning methods in a large and dynamic environment, we find that the classical baseline produces more stable and better performing policies overall.

For agents

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

get_harvested_code_for_paper("2202.12180")
get_code_for_paper("2202.12180")
have("2202.12180")

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

curl https://syntology.ai/api/ran/2202.12180.json

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

[![Syntology run record](https://syntology.ai/api/ran/2202.12180.svg)](https://syntology.ai/paper/2202.12180)

Connect an agent — have() is free.