{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HE7BB5FRAKS3WKS7SIJLC2R5DE","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":"c0ef2f38707f546e4ba2f82e33531c4cd68f4801b4b4d3ac1db75e4d3a4c3803","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T12:57:04Z","title_canon_sha256":"1bdd5c2280e8f5ff39965979110a6e5c730c3433eab05bd547e4cc1a1771208a"},"schema_version":"1.0","source":{"id":"1807.05827","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05827","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05827v4","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05827","created_at":"2026-05-17T23:45:52Z"},{"alias_kind":"pith_short_12","alias_value":"HE7BB5FRAKS3","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HE7BB5FRAKS3WKS7","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HE7BB5FR","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:89cfe8249b95ac53fd194c971ebd6404dbd44b3295e0253ebdedadab84b35802","target":"graph","created_at":"2026-05-17T23:45:52Z","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"},"paper":{"abstract_excerpt":"Experience replay (ER) is a fundamental component of off-policy deep reinforcement learning (RL). ER recalls experiences from past iterations to compute gradient estimates for the current policy, increasing data-efficiency. However, the accuracy of such updates may deteriorate when the policy diverges from past behaviors and can undermine the performance of ER. Many algorithms mitigate this issue by tuning hyper-parameters to slow down policy changes. An alternative is to actively enforce the similarity between policy and the experiences in the replay memory. We introduce Remember and Forget E","authors_text":"Guido Novati, Petros Koumoutsakos","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T12:57:04Z","title":"Remember and Forget for Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05827","kind":"arxiv","version":4},"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:ba26826c9f274ac5f5fb2730b53b163054139c674c4f6f75c438694d3dbf9949","target":"record","created_at":"2026-05-17T23:45:52Z","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":"c0ef2f38707f546e4ba2f82e33531c4cd68f4801b4b4d3ac1db75e4d3a4c3803","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T12:57:04Z","title_canon_sha256":"1bdd5c2280e8f5ff39965979110a6e5c730c3433eab05bd547e4cc1a1771208a"},"schema_version":"1.0","source":{"id":"1807.05827","kind":"arxiv","version":4}},"canonical_sha256":"393e10f4b102a5bb2a5f9212b16a3d1927f0ede5bf0f0a66ab2d7b44d9d8d817","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"393e10f4b102a5bb2a5f9212b16a3d1927f0ede5bf0f0a66ab2d7b44d9d8d817","first_computed_at":"2026-05-17T23:45:52.991421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:52.991421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ehAcwNZvJgAcQJuq7wHXAaGyt4D1ZC1EDs1DrqW7kwcTzLHpEJgk9rgMR+K4JZXJ2zGaOd+5zQKAdD5KqbJvDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:52.991828Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05827","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba26826c9f274ac5f5fb2730b53b163054139c674c4f6f75c438694d3dbf9949","sha256:89cfe8249b95ac53fd194c971ebd6404dbd44b3295e0253ebdedadab84b35802"],"state_sha256":"dc5e5d4cfbb32f6b2876104b451255265d9c68052de3c8a850a883fe55682a2e"}