{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/exploring-semantic-clustering-in-deep","title":"Exploring Semantic Clustering in Deep Reinforcement Learning for Video Games","arxiv_id":"2409.17411","date":"2024-09-25","proceeding":null,"authors":["Liang Zhang","Justin Lieffers","Adarsh Pyarelal"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2409.17411v3","url_pdf":"https://arxiv.org/pdf/2409.17411v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"online-clustering","task_name":"Online Clustering"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"semantic-similarity","task_name":"Semantic Similarity"},{"task_slug":"semantic-textual-similarity","task_name":"Semantic Textual Similarity"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.17411","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.17411"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/ualiangzhang/semantic_rl","reach":null}],"summary":{"ran":6,"ran_violates":1,"ran_fixture":1,"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"found_in_text":{"samples":17,"ran":9,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"48deda091b590818","entry":"BernoulliPd","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"48deda091b590818"}},{"code_sha256_prefix":"2d3c30ed29c2e7e3","entry":"BernoulliPdType","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d3c30ed29c2e7e3"}},{"code_sha256_prefix":"e9c69749d0d0f987","entry":"CategoricalPd","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e9c69749d0d0f987"}},{"code_sha256_prefix":"879ce0b5e2572140","entry":"DiagGaussianPd","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"879ce0b5e2572140"}},{"code_sha256_prefix":"23f71541edfa1c7d","entry":"DiagGaussianPdType","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"23f71541edfa1c7d"}},{"code_sha256_prefix":"7e6302fe75e8ce5b","entry":"MultiCategoricalPd","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e6302fe75e8ce5b"}},{"code_sha256_prefix":"8e365d56648e8635","entry":"_check_shape","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8e365d56648e8635"}},{"code_sha256_prefix":"bf4c4a4198b648b7","entry":"_squeeze_shape","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf4c4a4198b648b7"}},{"code_sha256_prefix":"42b26c636fbd04d3","entry":"adjust_shape","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"42b26c636fbd04d3"}},{"code_sha256_prefix":"bf5613ab09afe878","entry":"CategoricalPdType","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bf5613ab09afe878"}},{"code_sha256_prefix":"bd9b09139e3e25ac","entry":"MultiCategoricalPdType","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd9b09139e3e25ac"}},{"code_sha256_prefix":"f4660cce49b495df","entry":"Pd","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f4660cce49b495df"}},{"code_sha256_prefix":"8bf8ba4c04fac914","entry":"PdType","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8bf8ba4c04fac914"}},{"code_sha256_prefix":"deffac091561a023","entry":"PolicyWithValue","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"deffac091561a023"}},{"code_sha256_prefix":"3a78065dfb9d4a00","entry":"_matching_fc","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3a78065dfb9d4a00"}},{"code_sha256_prefix":"7b8dee118869a28b","entry":"fc","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b8dee118869a28b"}},{"code_sha256_prefix":"014517e29fd80d71","entry":"make_pdtype","repo":"ualiangzhang/semantic_rl","repo_kind":"found_in_text","path":"baselines/common/spolicies.py","file_url":"https://github.com/ualiangzhang/semantic_rl/blob/HEAD/baselines/common/spolicies.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"014517e29fd80d71"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}