SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.06858 · ICML · 2021

LTL2Action: Generalizing LTL Instructions for Multi-Task RL

Andrew Li, Pashootan Vaezipoor, Rodrigo Toro Icarte, Sheila Mcilraith

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 0 have no contract verdict; 1 failure of our instrument; 0 no recorded run), measured 2026-11-22; 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/2102.06858.json · badge: /api/ran/2102.06858.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
LTL2Action/LTL2Action canonical (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
progress Ran
ran; our contract draft was wrong, not the code
LTL2Action/LTL2Action/src/ltl_progression.py
code served (permissive licence) · get_code("225ebd2e12756d09")
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) 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.

# Setup code for progress function

# The function takes an LTL formula (either a string or a nested tuple structure)
# and a truth assignment (a dict or set of variable names that are true)

# Example 1: Simple propositional variable
ltl_formula_1 = 'p'
truth_assignment_1 = {'p', 'q'}

# Example 2: Negation
ltl_formula_2 = ('not', 'p')
truth_assignment_2 = {'q'}

# Example 3: And operation
ltl_formula_3 = ('and', 'p', 'q')
truth_assignment_3 = {'p', 'q'}

# Example 4: Or operation
ltl_formula_4 = ('or', 'p', 'q')
truth_assignment_4 = {'p'}

# Example 5: Next operator
ltl_formula_5 = ('next', 'p')
truth_assignment_5 = {'p'}

# Example 6: Eventually operator
ltl_formula_6 = ('eventually', 'p')
truth_assignment_6 = {'p'}

# Example 7: Always operator
ltl_formula_7 = ('always', 'p')
truth_assignment_7 = {'p'}

# Example 8: Until operator
ltl_formula_8 = ('until', 'p', 'q')
truth_assignment_8 = {'p', 'q'}

# Example 9: Complex nested formula
ltl_formula_9 = ('and', ('not', 'p'), ('or', 'q', 'r'))
truth_assignment_9 = {'q'}

# Use a simple case for ARGS
ARGS = {
    'ltl_formula': ('and', 'p', 'q'),
    'truth_assignment': {'p', 'q'}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 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

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 address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal language linear temporal logic (LTL) -and can specify a diversity of complex, temporally extended behaviours, including conditionals and alternative realizations. Our proposed learning approach exploits the compositional syntax and the semantics of LTL, enabling our RL agent to learn taskconditioned policies that generalize to new instructions, not observed during training. To reduce the overhead of learning LTL semantics, we introduce an environment-agnostic LTL pretraining scheme which improves sample-efficiency in downstream environments. Experiments on discrete and continuous domains target combinatorial task sets of up to ∼ 10 39 unique tasks and demonstrate the strength of our approach in learning to solve (unseen) tasks, given LTL instructions.

For agents

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

get_harvested_code_for_paper("2102.06858")
get_code_for_paper("2102.06858")
have("2102.06858")

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

curl https://syntology.ai/api/ran/2102.06858.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.06858.svg)](https://syntology.ai/paper/2102.06858)

Connect an agent — have() is free.