{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LUB7QRX2OWNT5P66ZQ34SHFT6T","short_pith_number":"pith:LUB7QRX2","schema_version":"1.0","canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","source":{"kind":"arxiv","id":"2211.06733","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Vector Quantized Encoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adarsh Pyarelal, Justin Lieffers, Liang Zhang","submitted_at":"2022-11-12T19:51:19Z","abstract_excerpt":"Human decision-making often involves combining similar states into categories and reasoning at the level of the categories rather than the actual states. Guided by this intuition, we propose a novel method for clustering state features in deep reinforcement learning (RL) methods to improve their interpretability. Specifically, we propose a plug-and-play framework termed \\emph{vector quantized reinforcement learning} (VQ-RL) that extends classic RL pipelines with an auxiliary classification task based on vector quantized (VQ) encoding and aligns with policy training. The VQ encoding method cate"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.06733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T19:51:19Z","cross_cats_sorted":[],"title_canon_sha256":"6925f55a225eddca11bc6a842455b15b6c8fe3c6345422f06f76784b97dea903","abstract_canon_sha256":"cdc9afcdb75641e1d31e960f43116c2b364276017e1487b223456c0e078b00e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:44.699286Z","signature_b64":"rNxCATwI10defIK8rbHmGjaZ1FqqWxPNuIhFzSDpK591/vQWy6nNKWjUz+Iwk3ILstN8MVq6D2OvSGg/FZ7PDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","last_reissued_at":"2026-07-05T05:15:44.698802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:44.698802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Vector Quantized Encoding","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adarsh Pyarelal, Justin Lieffers, Liang Zhang","submitted_at":"2022-11-12T19:51:19Z","abstract_excerpt":"Human decision-making often involves combining similar states into categories and reasoning at the level of the categories rather than the actual states. Guided by this intuition, we propose a novel method for clustering state features in deep reinforcement learning (RL) methods to improve their interpretability. Specifically, we propose a plug-and-play framework termed \\emph{vector quantized reinforcement learning} (VQ-RL) that extends classic RL pipelines with an auxiliary classification task based on vector quantized (VQ) encoding and aligns with policy training. The VQ encoding method cate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06733","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.06733/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.06733","created_at":"2026-07-05T05:15:44.698871+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.06733v1","created_at":"2026-07-05T05:15:44.698871+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06733","created_at":"2026-07-05T05:15:44.698871+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUB7QRX2OWNT","created_at":"2026-07-05T05:15:44.698871+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUB7QRX2OWNT5P66","created_at":"2026-07-05T05:15:44.698871+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUB7QRX2","created_at":"2026-07-05T05:15:44.698871+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20327","citing_title":"TADT-CSA: Temporal Advantage Decision Transformer with Contrastive State Abstraction for Generative Recommendation","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T","json":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T.json","graph_json":"https://pith.science/api/pith-number/LUB7QRX2OWNT5P66ZQ34SHFT6T/graph.json","events_json":"https://pith.science/api/pith-number/LUB7QRX2OWNT5P66ZQ34SHFT6T/events.json","paper":"https://pith.science/paper/LUB7QRX2"},"agent_actions":{"view_html":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T","download_json":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T.json","view_paper":"https://pith.science/paper/LUB7QRX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.06733&json=true","fetch_graph":"https://pith.science/api/pith-number/LUB7QRX2OWNT5P66ZQ34SHFT6T/graph.json","fetch_events":"https://pith.science/api/pith-number/LUB7QRX2OWNT5P66ZQ34SHFT6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/action/storage_attestation","attest_author":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/action/author_attestation","sign_citation":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/action/citation_signature","submit_replication":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/action/replication_record"}},"created_at":"2026-07-05T05:15:44.698871+00:00","updated_at":"2026-07-05T05:15:44.698871+00:00"}