SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.13231 · 2021

AndroidEnv: A Reinforcement Learning Platform for Android

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 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, 1 violated it and 1 has no contract verdict; 2 failures of our instrument; 1 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/2105.13231.json · badge: /api/ran/2105.13231.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
deepmind/android_env canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
yizhangliu/android_env_for_windows community (classifier label)
classifier basis not recorded on the link
2 ran · 1 no recorded run
FunctionStatusWhere it lives
build_tree_from_dumpsys_output Ran
ran; our contract draft was wrong, not the code
deepmind/android_env/android_env/components/app_screen_checker.py
code served (permissive licence) · get_code("0258648ec8cfc596")
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 _DumpsysNode. 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.

from collections.abc import Callable

dumpsys_output = """root_service
  service_one
    property_a: value_a
    property_b: value_b
  service_two
    sub_service
      detail_x: info_x
    property_c: value_c
  empty_service"""

ARGS = {
    "dumpsys_output": dumpsys_output
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type _DumpsysNode — a _DumpsysNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a _DumpsysNode 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
build_tree_from_dumpsys_output Ran
ran; our contract draft was wrong, not the code
yizhangliu/android_env_for_windows/android_env/components/app_screen_checker.py
code served (permissive licence) · get_code("0f7249a0adf69d49")
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 DumpsysNode. 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
from typing import Callable, List, Optional, Sequence, Pattern

# Build a sample dumpsys output string
dumpsys_output = """Service1
  Component1
    Property1: value1
    Property2: value2
  Component2
    SubComponent1
      Detail1: data1
Service2
  Component3
    Property3: value3"""

ARGS = {
    'dumpsys_output': dumpsys_output
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl, numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DumpsysNode — a DumpsysNode output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DumpsysNode 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
is_existing_emulator_provided Ran
ran on a synthesized input
yizhangliu/android_env_for_windows/android_env/components/emulator_simulator.py
code served (permissive licence) · get_code("f85e9d3b8c47e47a")
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 bool, 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
from typing import Any, Dict, Optional, List

# Construct valid arguments for is_existing_emulator_provided
# The function checks if launcher_args dict has 'adb_port', 'emulator_console_port', and 'grpc_port'

ARGS = {
    "launcher_args": {
        "adb_port": 5037,
        "emulator_console_port": 5554,
        "grpc_port": 8554
    }
}
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 bool, 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
matches_path Ran
ran, violated the contract we drafted
deepmind/android_env/android_env/components/app_screen_checker.py
code served (permissive licence) · get_code("2a99af3a1806d6bf")
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 bool, 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 re

# Create sample dumpsys output that matches the expected hierarchy
dumpsys_output = """Current Activity Manager state:
  mResumedActivity: ActivityRecord{abc123}
  View Hierarchy:
    DecorView{id=1000001, visibility=VISIBLE}
      LinearLayout{id=1000002}
        FrameLayout{id=1000003}
          TextView{id=1000004, text='Hello'}
"""

# Create regex patterns to match the view hierarchy path
# These will be tested sequentially against children of each node
expected_path = [
    re.compile(r'DecorView.*'),
    re.compile(r'LinearLayout.*'),
    re.compile(r'FrameLayout.*'),
]

ARGS = {
    'dumpsys_activity_output': dumpsys_output,
    'expected_view_hierarchy_path': expected_path,
    'max_levels': 0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
absl — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type bool, 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
matches_path Not yet run
unverified (harvested, no recorded run)
yizhangliu/android_env_for_windows/android_env/components/app_screen_checker.py
code served (permissive licence) · get_code("1ed5530621db6f05")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
build_tree_from_dumpsys_output 1 other paper
1 later
2305.08144 (2023-05)
Mobile-Env: Building Qualified Evaluation Benchmarks for LLM-GUI Interaction

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 introduce AndroidEnv, an open-source platform for Reinforcement Learning (RL) research built on top of the Android ecosystem. AndroidEnv allows RL agents to interact with a wide variety of apps and services commonly used by humans through a universal touchscreen interface. Since agents train on a realistic simulation of an Android device, they have the potential to be deployed on real devices. In this report, we give an overview of the environment, highlighting the significant features it provides for research, and we present an empirical evaluation of some popular reinforcement learning agents on a set of tasks built on this platform.

For agents

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

get_harvested_code_for_paper("2105.13231")
get_code_for_paper("2105.13231")
have("2105.13231")

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

curl https://syntology.ai/api/ran/2105.13231.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.13231.svg)](https://syntology.ai/paper/2105.13231)

Connect an agent — have() is free.