SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1908.04777 · 2019

Learn How to Cook a New Recipe in a New House: Using Map Familiarization, Curriculum Learning, and Bandit Feedback to Learn Families of Text-Based Adventure Games

arXiv · PDF · Open in the Atlas

Code that ran

1 of 1 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; 0 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/1908.04777.json · badge: /api/ran/1908.04777.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
yinxusen/deepword canonical (classifier label)
classifier basis: census
1 ran · 0 no recorded run
FunctionStatusWhere it lives
scores_of_tiers Ran
ran on a synthesized input
yinxusen/deepword/python/deepword/eval_games.py
code served (permissive licence) · get_code("5ee8d5164098514b")
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 dict. 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 import namedtuple
from typing import Dict

EvalResult = namedtuple('EvalResult', ('score', 'positive_score', 'negative_score', 'max_score', 'steps', 'won', 'action_list'))

agg_per_game = {
    'game1+recipe1': EvalResult(score=80, positive_score=10, negative_score=2, max_score=100, steps=50, won=True, action_list=[1, 2, 3]),
    'game2+recipe1': EvalResult(score=70, positive_score=8, negative_score=3, max_score=100, steps=45, won=False, action_list=[1, 2]),
    'game3+recipe2': EvalResult(score=90, positive_score=12, negative_score=1, max_score=100, steps=55, won=True, action_list=[1, 2, 3, 4]),
    'game4+recipe2': EvalResult(score=60, positive_score=6, negative_score=5, max_score=100, steps=40, won=False, action_list=[1]),
    'game5+recipe3': EvalResult(score=75, positive_score=9, negative_score=2, max_score=100, steps=48, won=True, action_list=[1, 2, 3]),
    'game6+recipe3': EvalResult(score=85, positive_score=11, negative_score=1, max_score=100, steps=52, won=True, action_list=[1, 2, 3, 4]),
    'game7+go6': EvalResult(score=50, positive_score=5, negative_score=4, max_score=100, steps=35, won=False, action_list=[1]),
    'game8+go6': EvalResult(score=65, positive_score=7, negative_score=3, max_score=100, steps=42, won=False, action_list=[1, 2]),
    'game9+go9': EvalResult(score=40, positive_score=4, negative_score=6, max_score=100, steps=30, won=False, action_list=[1]),
    'game10+go9': EvalResult(score=55, positive_score=5, negative_score=5, max_score=100, steps=38, won=False, action_list=[1, 2]),
    'game11+go12': EvalResult(score=30, positive_score=3, negative_score=8, max_score=100, steps=25, won=False, action_list=[1]),
    'game12+go12': EvalResult(score=45, positive_score=4, negative_score=7, max_score=100, steps=32, won=False, action_list=[1, 2]),
}

ARGS = {
    'agg_per_game': agg_per_game
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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

Also present in other papers' code

Of 1 samples lifted from this paper's linked repositories, 1 carry a function identity and 0 do not. Of the 1 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 1 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 consider the task of learning to play families of text-based computer adventure games, i.e., fully textual environments with a common theme (e.g. cooking) and goal (e.g. prepare a meal from a recipe) but with different specifics; new instances of such games are relatively straightforward for humans to master after a brief exposure to the genre but have been curiously difficult for computer agents to learn. We find that the deep Q-learning strategies that have been successfully leveraged for superhuman performance in single-instance action video games can be applied to learn families of text video games when adopting simple strategies that correlate with human-like learning behavior. Specifically, we build agents that learn to tackle simple scenarios before more complex ones using curriculum learning, that familiarize themselves in an unfamiliar environment by navigating before acting, and that explore uncertain environments more thoroughly using contextual multi-armed bandit decision policies. We demonstrate improved task completion rates over reasonable baselines when evaluating on never-before-seen games of that theme.

For agents

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

get_harvested_code_for_paper("1908.04777")
get_code_for_paper("1908.04777")
have("1908.04777")

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

curl https://syntology.ai/api/ran/1908.04777.json

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

[![Syntology run record](https://syntology.ai/api/ran/1908.04777.svg)](https://syntology.ai/paper/1908.04777)

Connect an agent — have() is free.