SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.12770 · 2020

BabyAI 1.1

arXiv · PDF · Open in the Atlas

Code that ran

2 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 2 have no contract verdict; 0 failures of our instrument; 7 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/2007.12770.json · badge: /api/ran/2007.12770.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
mila-iqia/babyai canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
mila-udem/babyai community (classifier label)
classifier basis not recorded on the link
2 ran · 6 no recorded run
FunctionStatusWhere it lives
evaluate Ran
ran on a synthesized input
mila-udem/babyai/babyai/evaluate.py
code served (permissive licence) · get_code("5ddbfe9ab59cd4a4")
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.

import torch
import torch.nn as nn


class SimpleAgent:
    def __init__(self):
        self.model = SimpleModel()
        self.last_reward = 0
        self.last_done = False
    
    def on_reset(self):
        pass
    
    def act(self, obs):
        # Returns dict with 'action' key
        return {'action': 0}
    
    def analyze_feedback(self, reward, done):
        self.last_reward = reward
        self.last_done = done


class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 2)
    
    def forward(self, x):
        return self.linear(x)


class SimpleEnv:
    def __init__(self):
        self.step_count = 0
        self.max_steps = 3
    
    def reset(self):
        self.step_count = 0
        return torch.randn(4)
    
    def step(self, action):
        self.step_count += 1
        obs = torch.randn(4)
        reward = 1.0
        done = self.step_count >= self.max_steps
        info = {}
        return obs, reward, done, info


torch.manual_seed(0)

agent = SimpleAgent()
env = SimpleEnv()
episodes = 2
model_agent = True
offsets = None

ARGS = {
    'agent': agent,
    'env': env,
    'episodes': episodes,
    'model_agent': model_agent,
    'offsets': offsets
}
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 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
evaluate_demo_agent Ran
ran on a synthesized input
mila-udem/babyai/babyai/evaluate.py
code served (permissive licence) · get_code("3a317898c18a2a4e")
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.

import torch

torch.manual_seed(0)

class DemoAgent:
    def __init__(self, demos):
        self.demos = demos

# Create mock demos - each demo is a list of frames
demo_1 = [torch.randn(4) for _ in range(5)]
demo_2 = [torch.randn(4) for _ in range(3)]
demo_3 = [torch.randn(4) for _ in range(7)]

agent = DemoAgent(demos=[demo_1, demo_2, demo_3])

ARGS = {
    'agent': agent,
    'episodes': 2
}
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 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
get_model_dir Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/utils/model.py
code served (permissive licence) · get_code("45eb1b6abf367f37")
How it ran

no invocation recorded.

get_model_path Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/utils/model.py
code served (permissive licence) · get_code("1afd6a43e76db402")
How it ran

no invocation recorded.

load_log Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/plotting.py
code served (permissive licence) · get_code("c22fe3da82c8f12a")
How it ran

no invocation recorded.

load_logs Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/plotting.py
code served (permissive licence) · get_code("683df5640b690d89")
How it ran

no invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/utils/model.py
code served (permissive licence) · get_code("129723f98ac7a958")
How it ran

no invocation recorded.

load_multiphase_log Not yet run
unverified (harvested, no recorded run)
mila-udem/babyai/babyai/plotting.py
code served (permissive licence) · get_code("f7e5c7e3ef155f53")
How it ran

no invocation recorded.

manhattan_distance Not yet run
unverified (harvested, no recorded run)
mila-iqia/babyai/babyai/bot.py
code served (permissive licence) · get_code("c1ffbae9fb9c6fc2")
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, 7 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 5 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.

FunctionAlso present inEarliest-datedOthers named
evaluate 2 other papers
1 dated earlier, 1 later
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
2306.00323 (2023-06)
Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
evaluate_demo_agent 2 other papers
1 dated earlier, 1 later
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
2306.00323 (2023-06)
Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
get_model_path 2 other papers
1 dated earlier, 1 later
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
2306.00323 (2023-06)
Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
manhattan_distance 2 other papers
1 dated earlier, 1 later
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
2306.00323 (2023-06)
Thought Cloning: Learning to Think while Acting by Imitating Human Thinking
get_model_dir 1 other paper
1 dated earlier
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
load_log 1 other paper
1 dated earlier
1810.08272 (2018-10)
BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning
load_model 1 other paper
1 later
2306.00323 (2023-06)
Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

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

The BabyAI platform is designed to measure the sample efficiency of training an agent to follow grounded-language instructions. BabyAI 1.0 presents baseline results of an agent trained by deep imitation or reinforcement learning. BabyAI 1.1 improves the agent's architecture in three minor ways. This increases reinforcement learning sample efficiency by up to 3 times and improves imitation learning performance on the hardest level from 77 % to 90.4 %. We hope that these improvements increase the computational efficiency of BabyAI experiments and help users design better agents.

For agents

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

get_harvested_code_for_paper("2007.12770")
get_code_for_paper("2007.12770")
have("2007.12770")

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

curl https://syntology.ai/api/ran/2007.12770.json

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

[![Syntology run record](https://syntology.ai/api/ran/2007.12770.svg)](https://syntology.ai/paper/2007.12770)

Connect an agent — have() is free.