{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6LJ2S236EH6B3GBS6WLXPUDZR","short_pith_number":"pith:G6LJ2S23","schema_version":"1.0","canonical_sha256":"37969d4b5bf10fe0ecc197acbbbe83cc5e5df30fe7248e473ed088258054e95c","source":{"kind":"arxiv","id":"2306.10698","version":6},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenxu Wang, Jie Fu, Junge Zhang, Liuyu Xiang, Tianyu Zheng, Yaodong Yang, Yonggang Jin, Zhaofeng He","submitted_at":"2023-06-19T04:48:36Z","abstract_excerpt":"Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities. In contrast, humans rely on their hippocampus to retrieve relevant information from past experiences of relevant tasks, which guides their decision-making when learning a new task, rather than exclusively depending on environmental interactions. Nevertheless, designing a hippocampus-like module for an agent to incorporate past experiences into established reinforcement learning algorithms presents "},"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":"2306.10698","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-19T04:48:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4ce25a8f27319537454bb3abc19539da082e8c02cfd6d8a9c9af08318255436e","abstract_canon_sha256":"2d7f6234a4659d52305e63d4ba60eed1689d5c5c706f64c505e4e1f4d9569782"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:58.241095Z","signature_b64":"FMxqJ+AS8Yi0EjyiiFLegIB2eWggrsaf8jLOtiI7i88qJxppkZUcNjP2FT7sCncpWSyPxKrlD3sMbWfp8axuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37969d4b5bf10fe0ecc197acbbbe83cc5e5df30fe7248e473ed088258054e95c","last_reissued_at":"2026-07-05T07:52:58.240650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:58.240650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Task-Adaptive Retrieval via Hypernetwork","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chenxu Wang, Jie Fu, Junge Zhang, Liuyu Xiang, Tianyu Zheng, Yaodong Yang, Yonggang Jin, Zhaofeng He","submitted_at":"2023-06-19T04:48:36Z","abstract_excerpt":"Deep reinforcement learning algorithms are usually impeded by sampling inefficiency, heavily depending on multiple interactions with the environment to acquire accurate decision-making capabilities. In contrast, humans rely on their hippocampus to retrieve relevant information from past experiences of relevant tasks, which guides their decision-making when learning a new task, rather than exclusively depending on environmental interactions. Nevertheless, designing a hippocampus-like module for an agent to incorporate past experiences into established reinforcement learning algorithms presents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10698","kind":"arxiv","version":6},"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/2306.10698/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":"2306.10698","created_at":"2026-07-05T07:52:58.240706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10698v6","created_at":"2026-07-05T07:52:58.240706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10698","created_at":"2026-07-05T07:52:58.240706+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6LJ2S236EH6","created_at":"2026-07-05T07:52:58.240706+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6LJ2S236EH6B3GB","created_at":"2026-07-05T07:52:58.240706+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6LJ2S23","created_at":"2026-07-05T07:52:58.240706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR","json":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR.json","graph_json":"https://pith.science/api/pith-number/G6LJ2S236EH6B3GBS6WLXPUDZR/graph.json","events_json":"https://pith.science/api/pith-number/G6LJ2S236EH6B3GBS6WLXPUDZR/events.json","paper":"https://pith.science/paper/G6LJ2S23"},"agent_actions":{"view_html":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR","download_json":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR.json","view_paper":"https://pith.science/paper/G6LJ2S23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10698&json=true","fetch_graph":"https://pith.science/api/pith-number/G6LJ2S236EH6B3GBS6WLXPUDZR/graph.json","fetch_events":"https://pith.science/api/pith-number/G6LJ2S236EH6B3GBS6WLXPUDZR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR/action/storage_attestation","attest_author":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR/action/author_attestation","sign_citation":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR/action/citation_signature","submit_replication":"https://pith.science/pith/G6LJ2S236EH6B3GBS6WLXPUDZR/action/replication_record"}},"created_at":"2026-07-05T07:52:58.240706+00:00","updated_at":"2026-07-05T07:52:58.240706+00:00"}