Papers › ASNets: Deep Learning for Generalised Planning

ASNets: Deep Learning for Generalised Planning

4 Aug 2019arXiv:1908.01362archive 2025-07-28

Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie

In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network architecture that exploits the relational structure of (P)PDDL planning problems to learn a common set of weights that can be applied to any problem in a domain. By mimicking the actions chosen by a traditional, non-learning planner on a handful of small problems in a domain, ASNets are able to learn a generalised reactive policy that can quickly solve much larger instances from the domain. This work extends the ASNet architecture to make it more expressive, while still remaining invariant to a range of symmetries that exist in PPDDL problems. We also present a thorough experimental evaluation of ASNets, including a comparison with heuristic search planners on seven probabilistic and deterministic domains, an extended evaluation on over 18,000 Blocksworld instances, and an ablation study. Finally, we show that sparsity-inducing regularisation can produce ASNets that are compact enough for humans to understand, yielding insights into how the structure of ASNets allows them to generalise across a domain.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 18 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 18 samples from 1 repository, 12 ran (12 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

qxcv/asnets officialmentioned in paperMITSyntology: 18 samples, 12 ran (0 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

12ran
6unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from qxcv/asnets. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

qxcv/asnets official repository 18 samples, 12 ran (0 instrument-failed) · 6 unverified
extract_all_domains_problems asnets/asnets/pddl_utils.py ran MIT (permissive) · 1d44813d2c760247 · report fixture: signature pddl_files:list/1/str · returned tuple · level recorded 2026-09-25
find_tail_cycle asnets/asnets/py_utils.py ran fingerprinted MIT (permissive) · 01894c8c99a5c3bc · report fixture: signature item_list:list/1/int, max_cycle_len:int/0/int · returned tuple · level recorded 2026-09-25
format_state_for_ssipp asnets/asnets/ssipp_interface.py ran MIT (permissive) · ca7dfed8da5f2147 · report fixture: signature all_props:list/1/tuple · returned str · level recorded 2026-09-25
get_plan_file_path asnets/asnets/fd_interface.py ran MIT (permissive) · d92b7dc4a1776ba4 · report fixture: signature root_dir:str/0/str, base_name:str/0/str · returned str · level recorded 2026-09-25
make_bound_prop asnets/asnets/prob_dom_meta.py ran MIT (permissive) · 8db9068b171ab385 · report fixture: signature mdpsim_ground_prop:GroundProp/0/? · returned BoundProp · level recorded 2026-09-25
make_unbound_prop asnets/asnets/prob_dom_meta.py ran MIT (permissive) · c70adc0ea5536072 · report fixture: signature mdpsim_lifted_prop:MockLiftedProp/0/? · returned UnboundProp · level recorded 2026-09-25
parse_problem_args asnets/asnets/mdpsim_utils.py ran MIT (permissive) · fab473cbc462543e · report fixture: signature mdpsim_module:MockMDPSimModule/0/?, pddls:list/1/str, problem_name:str/0/str · returned dict · level recorded 2026-09-25
parse_sexprs asnets/asnets/pddl_utils.py ran MIT (permissive) · eba72f2486b730d0 · report fixture: signature ppddl_txt:str/0/str · returned HList · level recorded 2026-09-25
set_up_ssipp asnets/asnets/ssipp_interface.py ran MIT (permissive) · 29bb436de3ba7e0b · report fixture: signature ssipp_module:MockSSIPPModule/0/?, pddl_paths:list/1/str, problem_name:str/0/str · returned dict · level recorded 2026-09-25
strip_parens asnets/asnets/py_utils.py ran MIT (permissive) · 2776f2994efc5176 · report fixture: signature thing:str/0/str · returned str · level recorded 2026-09-25
to_local asnets/asnets/multiprob.py ran MIT (permissive) · 211a1968113927a3 · report fixture: signature obj:dict/0/? · returned dict · level recorded 2026-09-25
weak_ref_to asnets/asnets/py_utils.py ran MIT (permissive) · ef639be154fac681 · report fixture: signature obj:SimpleObject/0/? · returned ProxyType · level recorded 2026-09-25
can_profile asnets/asnets/prof_utils.py unverified MIT (permissive) · f3b50583da62f483 · report
hlist_to_sexprs asnets/asnets/pddl_utils.py unverified MIT (permissive) · 4460d2adcc6338aa · report
make_unbound_action asnets/asnets/prob_dom_meta.py unverified MIT (permissive) · facfe8f2ba36c6f5 · report
run_fd_or_timeout asnets/asnets/fd_interface.py unverified MIT (permissive) · 5ee146b62834fec7 · report
run_fd_raw asnets/asnets/fd_interface.py unverified MIT (permissive) · 7434fe8e7707e998 · report
wait_exists_polling asnets/asnets/multiprob.py unverified MIT (permissive) · 004f8baf6f764d3b · report

Tasks

Deep LearningHeuristic Search

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections