{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H7J5H6LL7GUZ4NFWUSNMGHSNTP","short_pith_number":"pith:H7J5H6LL","schema_version":"1.0","canonical_sha256":"3fd3d3f96bf9a99e34b6a49ac31e4d9beb89028a6180d9ac7e77edcdd8f8cc51","source":{"kind":"arxiv","id":"2501.18093","version":1},"attestation_state":"computed","paper":{"title":"Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bruce A. MacDonald, Henry Williams, Hoda Yamani, Lee Violet C. Ong, Yuning Xing","submitted_at":"2025-01-30T02:09:35Z","abstract_excerpt":"Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of reward prediction errors (RPEs) in biological "},"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":"2501.18093","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-30T02:09:35Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"e9e32b52c85fd424319c9dd3730011784c3b1a1ca7471d07980d6e798d45f190","abstract_canon_sha256":"09b2b0826ca0111898d0afcf78eff74a33b40c23e19135d2a6d2f78713ff2208"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:06.938149Z","signature_b64":"2eXp84OvA1NGm0QRhbGyOK5vKtF7hQIMt0aIIoJhvswRKyYDaAfirKpwe9IyL59yz1LiLf7vQPiTEnITNPi+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fd3d3f96bf9a99e34b6a49ac31e4d9beb89028a6180d9ac7e77edcdd8f8cc51","last_reissued_at":"2026-07-05T10:07:06.937672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:06.937672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward Prediction Error Prioritisation in Experience Replay: The RPE-PER Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Bruce A. MacDonald, Henry Williams, Hoda Yamani, Lee Violet C. Ong, Yuning Xing","submitted_at":"2025-01-30T02:09:35Z","abstract_excerpt":"Reinforcement Learning algorithms aim to learn optimal control strategies through iterative interactions with an environment. A critical element in this process is the experience replay buffer, which stores past experiences, allowing the algorithm to learn from a diverse range of interactions rather than just the most recent ones. This buffer is especially essential in dynamic environments with limited experiences. However, efficiently selecting high-value experiences to accelerate training remains a challenge. Drawing inspiration from the role of reward prediction errors (RPEs) in biological "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18093","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/2501.18093/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":"2501.18093","created_at":"2026-07-05T10:07:06.937740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18093v1","created_at":"2026-07-05T10:07:06.937740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18093","created_at":"2026-07-05T10:07:06.937740+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7J5H6LL7GUZ","created_at":"2026-07-05T10:07:06.937740+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7J5H6LL7GUZ4NFW","created_at":"2026-07-05T10:07:06.937740+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7J5H6LL","created_at":"2026-07-05T10:07:06.937740+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/H7J5H6LL7GUZ4NFWUSNMGHSNTP","json":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP.json","graph_json":"https://pith.science/api/pith-number/H7J5H6LL7GUZ4NFWUSNMGHSNTP/graph.json","events_json":"https://pith.science/api/pith-number/H7J5H6LL7GUZ4NFWUSNMGHSNTP/events.json","paper":"https://pith.science/paper/H7J5H6LL"},"agent_actions":{"view_html":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP","download_json":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP.json","view_paper":"https://pith.science/paper/H7J5H6LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18093&json=true","fetch_graph":"https://pith.science/api/pith-number/H7J5H6LL7GUZ4NFWUSNMGHSNTP/graph.json","fetch_events":"https://pith.science/api/pith-number/H7J5H6LL7GUZ4NFWUSNMGHSNTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP/action/storage_attestation","attest_author":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP/action/author_attestation","sign_citation":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP/action/citation_signature","submit_replication":"https://pith.science/pith/H7J5H6LL7GUZ4NFWUSNMGHSNTP/action/replication_record"}},"created_at":"2026-07-05T10:07:06.937740+00:00","updated_at":"2026-07-05T10:07:06.937740+00:00"}