Papers › Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing

6 Jul 2018NeurIPS 2018 12arXiv:1807.02322archive 2025-07-28

Chen Liang, Mohammad Norouzi, Jonathan Berant, Quoc Le, Ni Lao

We present Memory Augmented Policy Optimization (MAPO), a simple and novel way to leverage a memory buffer of promising trajectories to reduce the variance of policy gradient estimate. MAPO is applicable to deterministic environments with discrete actions, such as structured prediction and combinatorial optimization tasks. We express the expected return objective as a weighted sum of two terms: an expectation over the high-reward trajectories inside the memory buffer, and a separate expectation over trajectories outside the buffer. To make an efficient algorithm of MAPO, we propose: (1) memory weight clipping to accelerate and stabilize training; (2) systematic exploration to discover high-reward trajectories; (3) distributed sampling from inside and outside of the memory buffer to scale up training. MAPO improves the sample efficiency and robustness of policy gradient, especially on tasks with sparse rewards. We evaluate MAPO on weakly supervised program synthesis from natural language (semantic parsing). On the WikiTableQuestions benchmark, we improve the state-of-the-art by 2.6%, achieving an accuracy of 46.3%. On the WikiSQL benchmark, MAPO achieves an accuracy of 74.9% with only weak supervision, outperforming several strong baselines with full supervision. Our source code is available at https://github.com/crazydonkey200/neural-symbolic-machines

PaperPDFConference PDFCodeCode 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 15 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 13 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 0 ran (0 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

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

crazydonkey200/neural-symbolic-machines officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 13 samples, 7 ran (0 instrument-failed) · 6 unverified report
niansong1996/wassp mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Merging Weak and Active Supervision for Semantic Parsing (arXiv:1911.12986; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
pcyin/pytorch_neural_symbolic_machines mentioned on GitHubpytorchSyntology: not harvested report
theSparta/neural-symbolic-machines mentioned on GitHubtfApache-2.0Syntology: 2 samples, 0 ran · 2 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

15 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 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.

7ran
8unverified

Licence: 0 of the 15 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

crazydonkey200/neural-symbolic-machines official repository 13 samples, 7 ran (0 instrument-failed) · 6 unverified
attn_sum_bahdanau nsm/tf_utils.py ran Apache-2.0 (permissive) · c3104e5e2d8a40e4 · report fixture: signature v_attn:EagerTensor/1/float, keys:EagerTensor/3/float, query:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
attn_sum_dot nsm/tf_utils.py ran Apache-2.0 (permissive) · f1f2fe840e5c928e · report fixture: signature keys:EagerTensor/3/float, query:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
bleu_score in 10 papers nsm/nlp_utils.py ran fingerprinted Apache-2.0 (permissive) · 9073ba6a227f3a75 · report fixture: signature sentence:list/1/str, gold_sentence:list/1/str · returned float · level recorded 2026-09-25
create_lm_inputs_labels nsm/data_utils.py ran Apache-2.0 (permissive) · ba6719f38bfb57e9 · report fixture: signature dataset:list/1/list, vocab:MockVocab/0/? · returned tuple · level recorded 2026-09-25
create_seq2seq_inputs nsm/data_utils.py ran Apache-2.0 (permissive) · 451d8aadbc0755dd · report fixture: signature en_dataset:list/1/list, en_vocab:Vocab/0/?, de_dataset:list/1/list, de_vocab:Vocab/0/? · returned tuple · level recorded 2026-09-25
tensormul nsm/tf_utils.py ran Apache-2.0 (permissive) · cc1113db8b905bd0 · report fixture: signature t1:EagerTensor/3/float, t2:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-25
with_graph_variable_scope nsm/graph_factory.py ran Apache-2.0 (permissive) · d34fbdeb6f1be262 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-25
create_multilayer_fnn nsm/graph_factory.py unverified Apache-2.0 (permissive) · 42891135110a96ff · report
create_seq_mse_loss nsm/graph_factory.py unverified Apache-2.0 (permissive) · ee764e83c41c8784 · report
edit_distance in 13 papers nsm/nlp_utils.py unverified Apache-2.0 (permissive) · 54fb9ba175e6c08b · report
show_samples table/experiment.py unverified Apache-2.0 (permissive) · fce4ea795a572f61 · report
tokenize in 176 papers nsm/nlp_utils.py unverified Apache-2.0 (permissive) · 4fb20ccedc18c760 · report
unpack_program table/experiment.py unverified Apache-2.0 (permissive) · 5677f59fb39ed6c9 · report
theSparta/neural-symbolic-machines community (archive-listed) 2 samples, 0 ran · 2 unverified
create_features nsm/env_factory.py unverified Apache-2.0 (permissive) · 88efa45be6ac471a · report
value_to_index nsm/env_factory.py unverified Apache-2.0 (permissive) · 9817d521556a77fa · report

Tasks

Combinatorial OptimizationProgram SynthesisSemantic ParsingStructured Prediction

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