{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YGYQ42DQF2HSUD4VJGVPII7DA5","short_pith_number":"pith:YGYQ42DQ","schema_version":"1.0","canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","source":{"kind":"arxiv","id":"2102.03261","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Prioritized Experience Replay: A Value Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ang A. Li, Chenglin Miao, Zongqing Lu","submitted_at":"2021-02-05T16:09:07Z","abstract_excerpt":"Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error ($|\\text{TD}|$) significantly improves the learning efficiency. But how $|\\text{TD}|$ is related to the importance of experience is not well understood. We address this problem from an economic perspective, by linking $|\\text{TD}|$ to value of experience, which is defined as the value added to the cumulative reward by accessing the experience. We theoretica"},"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":"2102.03261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","cross_cats_sorted":[],"title_canon_sha256":"a8a87fbd1e2aaf66d960fcd7e4831bed67c77da00797f137e0437bfa434291d1","abstract_canon_sha256":"221d1854c3ad68dbd2ef3d9f8ef7825b3ca0c8f812dda81cfbc07499922ec2bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:07.589828Z","signature_b64":"FCjogAkQw4Wa3Ssd02UejmFyTgmenZ3YT2T6bTQjgpFT63Nmdie7pN9yR40KphX32xBPwkjZrGoEQp9VnF6IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","last_reissued_at":"2026-07-05T02:13:07.589457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:07.589457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Prioritized Experience Replay: A Value Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ang A. Li, Chenglin Miao, Zongqing Lu","submitted_at":"2021-02-05T16:09:07Z","abstract_excerpt":"Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error ($|\\text{TD}|$) significantly improves the learning efficiency. But how $|\\text{TD}|$ is related to the importance of experience is not well understood. We address this problem from an economic perspective, by linking $|\\text{TD}|$ to value of experience, which is defined as the value added to the cumulative reward by accessing the experience. We theoretica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03261","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/2102.03261/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":"2102.03261","created_at":"2026-07-05T02:13:07.589528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.03261v1","created_at":"2026-07-05T02:13:07.589528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03261","created_at":"2026-07-05T02:13:07.589528+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGYQ42DQF2HS","created_at":"2026-07-05T02:13:07.589528+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGYQ42DQF2HSUD4V","created_at":"2026-07-05T02:13:07.589528+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGYQ42DQ","created_at":"2026-07-05T02:13:07.589528+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/YGYQ42DQF2HSUD4VJGVPII7DA5","json":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5.json","graph_json":"https://pith.science/api/pith-number/YGYQ42DQF2HSUD4VJGVPII7DA5/graph.json","events_json":"https://pith.science/api/pith-number/YGYQ42DQF2HSUD4VJGVPII7DA5/events.json","paper":"https://pith.science/paper/YGYQ42DQ"},"agent_actions":{"view_html":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5","download_json":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5.json","view_paper":"https://pith.science/paper/YGYQ42DQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.03261&json=true","fetch_graph":"https://pith.science/api/pith-number/YGYQ42DQF2HSUD4VJGVPII7DA5/graph.json","fetch_events":"https://pith.science/api/pith-number/YGYQ42DQF2HSUD4VJGVPII7DA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/action/storage_attestation","attest_author":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/action/author_attestation","sign_citation":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/action/citation_signature","submit_replication":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/action/replication_record"}},"created_at":"2026-07-05T02:13:07.589528+00:00","updated_at":"2026-07-05T02:13:07.589528+00:00"}