{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OOLFBEWZKM5KABL475FNKJZAW6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8447c3c82c5a2cd18031e72ac0209c971f6173d552124a88cdd9255e3afc46f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T14:39:39Z","title_canon_sha256":"1091d4f1abd0bb73671d143263249ab00284752f7acd1131fe2e601f835268e1"},"schema_version":"1.0","source":{"id":"2410.04498","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04498","created_at":"2026-05-28T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04498v2","created_at":"2026-05-28T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04498","created_at":"2026-05-28T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"OOLFBEWZKM5K","created_at":"2026-05-28T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"OOLFBEWZKM5KABL4","created_at":"2026-05-28T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"OOLFBEWZ","created_at":"2026-05-28T01:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:bdfb568b558feeb57796311873b6429c8d05408123199b5d7b8c598567e567e8","target":"graph","created_at":"2026-05-28T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.04498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Junliang Xing, Ling Liangn, Renye Yan, Yaozhong Gan, Yeshang Zhu, Yimao Cai, You Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T14:39:39Z","title":"AdaMemento: Adaptive Memory-Assisted Policy Optimization for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04498","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a97f62a8e087c55f23a060cd9a59143e3e01248ec2d102d4d3dcedb42a046d03","target":"record","created_at":"2026-05-28T01:05:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8447c3c82c5a2cd18031e72ac0209c971f6173d552124a88cdd9255e3afc46f3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T14:39:39Z","title_canon_sha256":"1091d4f1abd0bb73671d143263249ab00284752f7acd1131fe2e601f835268e1"},"schema_version":"1.0","source":{"id":"2410.04498","kind":"arxiv","version":2}},"canonical_sha256":"73965092d9533aa0057cff4ad52720b79d0cc443b150a403293e51d80f89646c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73965092d9533aa0057cff4ad52720b79d0cc443b150a403293e51d80f89646c","first_computed_at":"2026-05-28T01:05:10.074816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:05:10.074816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dNHpWOwRsxpwBVXeCl3K8eSbx7NuNdKXQ+P581duGTveTJ6HkgCBumuUdT1YLccCsSpmZjTAa5s0xwmRrlAnAA==","signature_status":"signed_v1","signed_at":"2026-05-28T01:05:10.075267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04498","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a97f62a8e087c55f23a060cd9a59143e3e01248ec2d102d4d3dcedb42a046d03","sha256:bdfb568b558feeb57796311873b6429c8d05408123199b5d7b8c598567e567e8"],"state_sha256":"58f6e741bc845b081ac58ff5f83acd2bc6aaa120f0ccc17393b0d92c844459f8"}