Papers › Exploring Semantic Clustering in Deep Reinforcement Learning for Video Games

Exploring Semantic Clustering in Deep Reinforcement Learning for Video Games

25 Sep 2024arXiv:2409.17411archive 2025-07-28

Liang Zhang, Justin Lieffers, Adarsh Pyarelal

In this paper, we investigate the semantic clustering properties of deep reinforcement learning (DRL) for video games, enriching our understanding of the internal dynamics of DRL and advancing its interpretability. In this context, semantic clustering refers to the inherent capacity of neural networks to internally group video inputs based on semantic similarity. To achieve this, we propose a novel DRL architecture that integrates a semantic clustering module featuring both feature dimensionality reduction and online clustering. This module seamlessly integrates into the DRL training pipeline, addressing instability issues observed in previous t-SNE-based analysis methods and eliminating the necessity for extensive manual annotation of semantic analysis. Through experiments, we validate the effectiveness of the proposed module and the semantic clustering properties in DRL for video games. Additionally, based on these properties, we introduce new analytical methods to help understand the hierarchical structure of policies and the semantic distribution within the feature space.

PaperPDFCode Syntology ranMethod as code

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 17 code samples harvested from 1 repository linked to this paper: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 17 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ualiangzhang/semantic_rl found in paper text by SyntologySyntology: 17 samples, 9 ran (2 instrument-failed) · 8 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

17 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 2 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.

1ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
6ran
8unverified

Licence: 0 of the 17 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 ualiangzhang/semantic_rl. “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.

ualiangzhang/semantic_rl found in paper text by Syntology 17 samples, 9 ran (2 instrument-failed) · 8 unverified
BernoulliPd baselines/common/spolicies.py ran MIT (permissive) · 48deda091b590818 · report fixture: returned BernoulliPd · level recorded 2026-09-22
BernoulliPdType baselines/common/spolicies.py ran MIT (permissive) · 2d3c30ed29c2e7e3 · report fixture: returned BernoulliPdType · level recorded 2026-09-22
CategoricalPd baselines/common/spolicies.py ran MIT (permissive) · e9c69749d0d0f987 · report fixture: returned CategoricalPd · level recorded 2026-09-22
DiagGaussianPd baselines/common/spolicies.py ran MIT (permissive) · 879ce0b5e2572140 · report fixture: returned DiagGaussianPd · level recorded 2026-09-22
DiagGaussianPdType baselines/common/spolicies.py ran MIT (permissive) · 23f71541edfa1c7d · report fixture: returned DiagGaussianPdType · level recorded 2026-09-22
MultiCategoricalPd baselines/common/spolicies.py ran MIT (permissive) · 7e6302fe75e8ce5b · report fixture: returned MultiCategoricalPd · level recorded 2026-09-22
_check_shape baselines/common/spolicies.py ran · violated contract MIT (permissive) · 8e365d56648e8635 · report fixture: signature placeholder_shape:list/1/int, data_shape:list/1/int · returned bool · level recorded 2026-09-22
_squeeze_shape baselines/common/spolicies.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · bf4c4a4198b648b7 · report fixture: signature shape:list/1/int · returned list · level recorded 2026-09-22
adjust_shape baselines/common/spolicies.py ran · our draft was wrong MIT (permissive) · 42b26c636fbd04d3 · report fixture: signature placeholder:MockPlaceholder/0/?, data:ndarray/3/float · returned ndarray · level recorded 2026-09-22
CategoricalPdType baselines/common/spolicies.py unverified MIT (permissive) · bf5613ab09afe878 · report
MultiCategoricalPdType baselines/common/spolicies.py unverified MIT (permissive) · bd9b09139e3e25ac · report
Pd baselines/common/spolicies.py unverified MIT (permissive) · f4660cce49b495df · report
PdType baselines/common/spolicies.py unverified MIT (permissive) · 8bf8ba4c04fac914 · report
PolicyWithValue baselines/common/spolicies.py unverified MIT (permissive) · deffac091561a023 · report
_matching_fc baselines/common/spolicies.py unverified MIT (permissive) · 3a78065dfb9d4a00 · report
fc in 16 papers baselines/common/spolicies.py unverified MIT (permissive) · 7b8dee118869a28b · report
make_pdtype baselines/common/spolicies.py unverified MIT (permissive) · 014517e29fd80d71 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for semantic clustering module (graph method: semantic clustering module). 18 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

  1. PolicyWithValue entry · level 0 · unverified · deffac091561a023
  2. adjust_shape helper · level 1 · ran · our draft was wrong · 42b26c636fbd04d3
  3. fc helper · level 0 · unverified · 7b8dee118869a28b
  4. make_pdtype helper · level 0 · unverified · 014517e29fd80d71
  5. _check_shape helper · level 1 · ran · violated contract · 8e365d56648e8635
  6. ortho_init helper · level 1 · ran · our draft was wrong · 0cb9b8299fe38738
  7. BernoulliPdType helper · level 1 · ran · 2d3c30ed29c2e7e3
  8. CategoricalPdType helper · level 0 · unverified · bf5613ab09afe878
  9. DiagGaussianPdType helper · level 1 · ran · 23f71541edfa1c7d
  10. MultiCategoricalPdType helper · level 0 · unverified · bd9b09139e3e25ac
  11. _squeeze_shape helper · level 1 · ran; the contract check could not run (RAISES) · bf4c4a4198b648b7
  12. BernoulliPd helper · level 1 · ran · 48deda091b590818
  13. PdType helper · level 0 · unverified · 8bf8ba4c04fac914
  14. _matching_fc helper · level 0 · unverified · 3a78065dfb9d4a00
  15. CategoricalPd helper · level 1 · ran · e9c69749d0d0f987
  16. DiagGaussianPd helper · level 1 · ran · 879ce0b5e2572140
  17. MultiCategoricalPd helper · level 1 · ran · 7e6302fe75e8ce5b
  18. Pd helper · level 0 · unverified · f4660cce49b495df

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2409.17411") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringDeep Reinforcement LearningDimensionality ReductionOnline ClusteringReinforcement LearningSemantic SimilaritySemantic Textual Similarityreinforcement-learning

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