{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:77A73QHOYMNXQ25SC3PI6JCUFC","short_pith_number":"pith:77A73QHO","schema_version":"1.0","canonical_sha256":"ffc1fdc0eec31b786bb216de8f245428bce6d34a57a675669228229795e36696","source":{"kind":"arxiv","id":"2211.00576","version":2},"attestation_state":"computed","paper":{"title":"Event Tables for Efficient Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Peter Stone, Peter Wurman, Samuel Barrett, Thomas J. Walsh, Varun Kompella","submitted_at":"2022-11-01T16:38:23Z","abstract_excerpt":"Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), which partitions an ER buffer into Event Tables, each capturing important subsequences of optimal behavior. We prove a theoretical advantage over the traditional monolithic buffer approach and combine SSET with an existing prioritized sampling strategy to further improve learning speed and stability. Empirical results in chall"},"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":"2211.00576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T16:38:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b68df3013c2d16efde804c92eefe77a39dab8d973385b52740463d506a15203d","abstract_canon_sha256":"09fda184bbcfb1767ec02d2d15897c5ed4c8743909fb888bec90fafbbeeeb880"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:54.658806Z","signature_b64":"5W5qEctadtZeziziSSvbbcAVou3JWu9kCaEzO2cAVI7Ruzz162eXpy9mkc4diUjWqTeVsgGwN5EvimV12RTuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc1fdc0eec31b786bb216de8f245428bce6d34a57a675669228229795e36696","last_reissued_at":"2026-07-05T06:21:54.658294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:54.658294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Event Tables for Efficient Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Peter Stone, Peter Wurman, Samuel Barrett, Thomas J. Walsh, Varun Kompella","submitted_at":"2022-11-01T16:38:23Z","abstract_excerpt":"Experience replay (ER) is a crucial component of many deep reinforcement learning (RL) systems. However, uniform sampling from an ER buffer can lead to slow convergence and unstable asymptotic behaviors. This paper introduces Stratified Sampling from Event Tables (SSET), which partitions an ER buffer into Event Tables, each capturing important subsequences of optimal behavior. We prove a theoretical advantage over the traditional monolithic buffer approach and combine SSET with an existing prioritized sampling strategy to further improve learning speed and stability. Empirical results in chall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00576","kind":"arxiv","version":2},"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/2211.00576/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":"2211.00576","created_at":"2026-07-05T06:21:54.658358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00576v2","created_at":"2026-07-05T06:21:54.658358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00576","created_at":"2026-07-05T06:21:54.658358+00:00"},{"alias_kind":"pith_short_12","alias_value":"77A73QHOYMNX","created_at":"2026-07-05T06:21:54.658358+00:00"},{"alias_kind":"pith_short_16","alias_value":"77A73QHOYMNXQ25S","created_at":"2026-07-05T06:21:54.658358+00:00"},{"alias_kind":"pith_short_8","alias_value":"77A73QHO","created_at":"2026-07-05T06:21:54.658358+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00642","citing_title":"Coachable agents for interactive gameplay","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC","json":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC.json","graph_json":"https://pith.science/api/pith-number/77A73QHOYMNXQ25SC3PI6JCUFC/graph.json","events_json":"https://pith.science/api/pith-number/77A73QHOYMNXQ25SC3PI6JCUFC/events.json","paper":"https://pith.science/paper/77A73QHO"},"agent_actions":{"view_html":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC","download_json":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC.json","view_paper":"https://pith.science/paper/77A73QHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00576&json=true","fetch_graph":"https://pith.science/api/pith-number/77A73QHOYMNXQ25SC3PI6JCUFC/graph.json","fetch_events":"https://pith.science/api/pith-number/77A73QHOYMNXQ25SC3PI6JCUFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC/action/storage_attestation","attest_author":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC/action/author_attestation","sign_citation":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC/action/citation_signature","submit_replication":"https://pith.science/pith/77A73QHOYMNXQ25SC3PI6JCUFC/action/replication_record"}},"created_at":"2026-07-05T06:21:54.658358+00:00","updated_at":"2026-07-05T06:21:54.658358+00:00"}