{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OOLFBEWZKM5KABL475FNKJZAW6","short_pith_number":"pith:OOLFBEWZ","schema_version":"1.0","canonical_sha256":"73965092d9533aa0057cff4ad52720b79d0cc443b150a403293e51d80f89646c","source":{"kind":"arxiv","id":"2410.04498","version":2},"attestation_state":"computed","paper":{"title":"AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junliang Xing, Ling Liangn, Renye Yan, Yaozhong Gan, Yeshang Zhu, Yimao Cai, You Wu","submitted_at":"2024-10-06T14:39:39Z","abstract_excerpt":"In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and reuse high-value policies, lacking a deeper refining and filtering of diverse past experiences and hence limiting the capability of memory. In this paper, we propose AdaMemento, an adaptive memory-enhanced RL framework. Instead of just memorizing positive past experiences, we design a memory-reflection module that exploits both positive and negative experiences"},"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":"2410.04498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T14:39:39Z","cross_cats_sorted":[],"title_canon_sha256":"1091d4f1abd0bb73671d143263249ab00284752f7acd1131fe2e601f835268e1","abstract_canon_sha256":"8447c3c82c5a2cd18031e72ac0209c971f6173d552124a88cdd9255e3afc46f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:10.075267Z","signature_b64":"dNHpWOwRsxpwBVXeCl3K8eSbx7NuNdKXQ+P581duGTveTJ6HkgCBumuUdT1YLccCsSpmZjTAa5s0xwmRrlAnAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73965092d9533aa0057cff4ad52720b79d0cc443b150a403293e51d80f89646c","last_reissued_at":"2026-05-28T01:05:10.074816Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:10.074816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junliang Xing, Ling Liangn, Renye Yan, Yaozhong Gan, Yeshang Zhu, Yimao Cai, You Wu","submitted_at":"2024-10-06T14:39:39Z","abstract_excerpt":"In sparse reward scenarios of reinforcement learning (RL), the memory mechanism provides promising shortcuts to policy optimization by reflecting on past experiences like humans. However, current memory-based RL methods simply store and reuse high-value policies, lacking a deeper refining and filtering of diverse past experiences and hence limiting the capability of memory. In this paper, we propose AdaMemento, an adaptive memory-enhanced RL framework. Instead of just memorizing positive past experiences, we design a memory-reflection module that exploits both positive and negative experiences"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04498","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/2410.04498/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":"2410.04498","created_at":"2026-05-28T01:05:10.074882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04498v2","created_at":"2026-05-28T01:05:10.074882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04498","created_at":"2026-05-28T01:05:10.074882+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOLFBEWZKM5K","created_at":"2026-05-28T01:05:10.074882+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOLFBEWZKM5KABL4","created_at":"2026-05-28T01:05:10.074882+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOLFBEWZ","created_at":"2026-05-28T01:05:10.074882+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/OOLFBEWZKM5KABL475FNKJZAW6","json":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6.json","graph_json":"https://pith.science/api/pith-number/OOLFBEWZKM5KABL475FNKJZAW6/graph.json","events_json":"https://pith.science/api/pith-number/OOLFBEWZKM5KABL475FNKJZAW6/events.json","paper":"https://pith.science/paper/OOLFBEWZ"},"agent_actions":{"view_html":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6","download_json":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6.json","view_paper":"https://pith.science/paper/OOLFBEWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04498&json=true","fetch_graph":"https://pith.science/api/pith-number/OOLFBEWZKM5KABL475FNKJZAW6/graph.json","fetch_events":"https://pith.science/api/pith-number/OOLFBEWZKM5KABL475FNKJZAW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6/action/storage_attestation","attest_author":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6/action/author_attestation","sign_citation":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6/action/citation_signature","submit_replication":"https://pith.science/pith/OOLFBEWZKM5KABL475FNKJZAW6/action/replication_record"}},"created_at":"2026-05-28T01:05:10.074882+00:00","updated_at":"2026-05-28T01:05:10.074882+00:00"}