{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ERJM7V76OKQVYVORMGYCTFAUJW","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":"afc0e012378a937e86b7fa1027e6972cf4948ae5c7e32c9af6bfb23dcab7e28f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:01:23Z","title_canon_sha256":"dd0479f47aeba32b39ddc15ff0b431f86d0b890194a11bd3c7e4599b9ad1ce3c"},"schema_version":"1.0","source":{"id":"1909.12255","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.12255","created_at":"2026-07-05T01:16:09Z"},{"alias_kind":"arxiv_version","alias_value":"1909.12255v3","created_at":"2026-07-05T01:16:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.12255","created_at":"2026-07-05T01:16:09Z"},{"alias_kind":"pith_short_12","alias_value":"ERJM7V76OKQV","created_at":"2026-07-05T01:16:09Z"},{"alias_kind":"pith_short_16","alias_value":"ERJM7V76OKQVYVOR","created_at":"2026-07-05T01:16:09Z"},{"alias_kind":"pith_short_8","alias_value":"ERJM7V76","created_at":"2026-07-05T01:16:09Z"}],"graph_snapshots":[{"event_id":"sha256:6882331dad068252ff079e778da1a279d1df17cac663a2ff4a52cecebdcd4002","target":"graph","created_at":"2026-07-05T01:16:09Z","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/1909.12255/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value-based methods constitute a fundamental methodology in planning and deep reinforcement learning (RL). In this paper, we propose to exploit the underlying structures of the state-action value function, i.e., Q function, for both planning and deep RL. In particular, if the underlying system dynamics lead to some global structures of the Q function, one should be capable of inferring the function better by leveraging such structures. Specifically, we investigate the low-rank structure, which widely exists for big data matrices. We verify empirically the existence of low-rank Q functions in t","authors_text":"Dina Katabi, Guo Zhang, Yuzhe Yang, Zhi Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:01:23Z","title":"Harnessing Structures for Value-Based Planning and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.12255","kind":"arxiv","version":3},"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":"sha256:9758f5090287bb34cafd324821996a65bee698e8ad8eff95a7c63ee1be2b50ee","target":"record","created_at":"2026-07-05T01:16:09Z","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":"afc0e012378a937e86b7fa1027e6972cf4948ae5c7e32c9af6bfb23dcab7e28f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-26T17:01:23Z","title_canon_sha256":"dd0479f47aeba32b39ddc15ff0b431f86d0b890194a11bd3c7e4599b9ad1ce3c"},"schema_version":"1.0","source":{"id":"1909.12255","kind":"arxiv","version":3}},"canonical_sha256":"2452cfd7fe72a15c55d161b02994144d9e53ff95d8a51a8dec9a61def6d9058d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2452cfd7fe72a15c55d161b02994144d9e53ff95d8a51a8dec9a61def6d9058d","first_computed_at":"2026-07-05T01:16:09.789691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:09.789691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hPMkSaBHU+KTzE61jjZCmJOMDKKQArTs2UegAviIfxLQcCFYyB4ZJSfaPMB9KOTU0pqBicHG3Nf5dAsd+NenBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:09.790183Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.12255","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9758f5090287bb34cafd324821996a65bee698e8ad8eff95a7c63ee1be2b50ee","sha256:6882331dad068252ff079e778da1a279d1df17cac663a2ff4a52cecebdcd4002"],"state_sha256":"c7203e3454fb3f2c9f6bf274e8181868cc87f88915351300dff3467824011054"}