{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:LUB7QRX2OWNT5P66ZQ34SHFT6T","short_pith_number":"pith:LUB7QRX2","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"},"canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","source":{"kind":"arxiv","id":"2211.06733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06733","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06733v1","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06733","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"LUB7QRX2OWNT","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"LUB7QRX2OWNT5P66","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"LUB7QRX2","created_at":"2026-07-05T05:15:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:LUB7QRX2OWNT5P66ZQ34SHFT6T","target":"record","payload":{"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"},"canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","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"},"source_kind":"arxiv","source_id":"2211.06733","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ysw/5ibwTNrAtlCmyni5Pez17qiGsg4KbPuIocJZoGHi8Et2rAIgol5wiko4wa855KPCCQ89+M6RWSPmjKfDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:06:00.716931Z"},"content_sha256":"f75eaf79777c86b645d4d56400daebdbcc2d064a49661001d9e7fe55e647c9ce","schema_version":"1.0","event_id":"sha256:f75eaf79777c86b645d4d56400daebdbcc2d064a49661001d9e7fe55e647c9ce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:LUB7QRX2OWNT5P66ZQ34SHFT6T","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xlcrXN4N4NeyxPnJzURCFdnfin74OtG8+NjiSbA9/ALtVaYsuy3YHALQWgrE0i7joov/6E3ljZx6G1u4I87BAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:06:00.717517Z"},"content_sha256":"72ad44404729e6ea120b950b1c760bfa54f3ea0f0885f2ed214b041e2ccd6bd7","schema_version":"1.0","event_id":"sha256:72ad44404729e6ea120b950b1c760bfa54f3ea0f0885f2ed214b041e2ccd6bd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/bundle.json","state_url":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T20:06:00Z","links":{"resolver":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T","bundle":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/bundle.json","state":"https://pith.science/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LUB7QRX2OWNT5P66ZQ34SHFT6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LUB7QRX2OWNT5P66ZQ34SHFT6T","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cdc9afcdb75641e1d31e960f43116c2b364276017e1487b223456c0e078b00e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T19:51:19Z","title_canon_sha256":"6925f55a225eddca11bc6a842455b15b6c8fe3c6345422f06f76784b97dea903"},"schema_version":"1.0","source":{"id":"2211.06733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06733","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06733v1","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06733","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_12","alias_value":"LUB7QRX2OWNT","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_16","alias_value":"LUB7QRX2OWNT5P66","created_at":"2026-07-05T05:15:44Z"},{"alias_kind":"pith_short_8","alias_value":"LUB7QRX2","created_at":"2026-07-05T05:15:44Z"}],"graph_snapshots":[{"event_id":"sha256:72ad44404729e6ea120b950b1c760bfa54f3ea0f0885f2ed214b041e2ccd6bd7","target":"graph","created_at":"2026-07-05T05:15:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.06733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adarsh Pyarelal, Justin Lieffers, Liang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T19:51:19Z","title":"Deep Reinforcement Learning with Vector Quantized Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06733","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f75eaf79777c86b645d4d56400daebdbcc2d064a49661001d9e7fe55e647c9ce","target":"record","created_at":"2026-07-05T05:15:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cdc9afcdb75641e1d31e960f43116c2b364276017e1487b223456c0e078b00e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-12T19:51:19Z","title_canon_sha256":"6925f55a225eddca11bc6a842455b15b6c8fe3c6345422f06f76784b97dea903"},"schema_version":"1.0","source":{"id":"2211.06733","kind":"arxiv","version":1}},"canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d03f846fa759b3ebfdecc37c91cb3f4daee425113edb126d6ac77a7959876bf","first_computed_at":"2026-07-05T05:15:44.698802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:44.698802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rNxCATwI10defIK8rbHmGjaZ1FqqWxPNuIhFzSDpK591/vQWy6nNKWjUz+Iwk3ILstN8MVq6D2OvSGg/FZ7PDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:44.699286Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f75eaf79777c86b645d4d56400daebdbcc2d064a49661001d9e7fe55e647c9ce","sha256:72ad44404729e6ea120b950b1c760bfa54f3ea0f0885f2ed214b041e2ccd6bd7"],"state_sha256":"ec869e0c17fde728d8df0e5dad8a9b6460e218e4b743cce7844d19d70d51350f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ayWrwGnNlbod03D37kBa6xln1hKrZhTZnKkc80xdWIKjaj9m49JZyNeWD0psrgx2P5hCaHYlWE2id7MmWIYrAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:06:00.722982Z","bundle_sha256":"f62245ec121bfd4ce2074f64212757385ce452156aecaac0556ee1347ffa980c"}}