{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DHXV4AWEK4G4VTNZK6LEMBZI3J","short_pith_number":"pith:DHXV4AWE","schema_version":"1.0","canonical_sha256":"19ef5e02c4570dcacdb95796460728da6554926ecfd6f58b8b2d96a9f821a9c0","source":{"kind":"arxiv","id":"2303.08690","version":2},"attestation_state":"computed","paper":{"title":"Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Rahimi-Kalahroudi, Harm van Seijen, Ida Momennejad, Janarthanan Rajendran, Sarath Chandar","submitted_at":"2023-03-15T15:21:26Z","abstract_excerpt":"One of the key behavioral characteristics used in neuroscience to determine whether the subject of study -- be it a rodent or a human -- exhibits model-based learning is effective adaptation to local changes in the environment, a particular form of adaptivity that is the focus of this work. In reinforcement learning, however, recent work has shown that modern deep model-based reinforcement-learning (MBRL) methods adapt poorly to local environment changes. An explanation for this mismatch is that MBRL methods are typically designed with sample-efficiency on a single task in mind and the require"},"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":"2303.08690","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-15T15:21:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8a00a7792633b8a1d60b510b5c666c4b1a1827f817eb6ef56d7cda45c27b99f7","abstract_canon_sha256":"b631857e6d078f552c3fa8d1fe0a1106d7efc4ff982f7e67da70ad2bd34a51fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:53.921160Z","signature_b64":"9ivM3LmnpwzFCvKKkh207DmCUOBCafne0ufR3xERo3kPNlS8oinkVts2eMzdHJ4FQwUgy0LQnlzRIl3Yeh51DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19ef5e02c4570dcacdb95796460728da6554926ecfd6f58b8b2d96a9f821a9c0","last_reissued_at":"2026-07-05T06:54:53.920806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:53.920806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Rahimi-Kalahroudi, Harm van Seijen, Ida Momennejad, Janarthanan Rajendran, Sarath Chandar","submitted_at":"2023-03-15T15:21:26Z","abstract_excerpt":"One of the key behavioral characteristics used in neuroscience to determine whether the subject of study -- be it a rodent or a human -- exhibits model-based learning is effective adaptation to local changes in the environment, a particular form of adaptivity that is the focus of this work. In reinforcement learning, however, recent work has shown that modern deep model-based reinforcement-learning (MBRL) methods adapt poorly to local environment changes. An explanation for this mismatch is that MBRL methods are typically designed with sample-efficiency on a single task in mind and the require"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.08690","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/2303.08690/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":"2303.08690","created_at":"2026-07-05T06:54:53.920863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.08690v2","created_at":"2026-07-05T06:54:53.920863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.08690","created_at":"2026-07-05T06:54:53.920863+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHXV4AWEK4G4","created_at":"2026-07-05T06:54:53.920863+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHXV4AWEK4G4VTNZ","created_at":"2026-07-05T06:54:53.920863+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHXV4AWE","created_at":"2026-07-05T06:54:53.920863+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/DHXV4AWEK4G4VTNZK6LEMBZI3J","json":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J.json","graph_json":"https://pith.science/api/pith-number/DHXV4AWEK4G4VTNZK6LEMBZI3J/graph.json","events_json":"https://pith.science/api/pith-number/DHXV4AWEK4G4VTNZK6LEMBZI3J/events.json","paper":"https://pith.science/paper/DHXV4AWE"},"agent_actions":{"view_html":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J","download_json":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J.json","view_paper":"https://pith.science/paper/DHXV4AWE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.08690&json=true","fetch_graph":"https://pith.science/api/pith-number/DHXV4AWEK4G4VTNZK6LEMBZI3J/graph.json","fetch_events":"https://pith.science/api/pith-number/DHXV4AWEK4G4VTNZK6LEMBZI3J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J/action/storage_attestation","attest_author":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J/action/author_attestation","sign_citation":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J/action/citation_signature","submit_replication":"https://pith.science/pith/DHXV4AWEK4G4VTNZK6LEMBZI3J/action/replication_record"}},"created_at":"2026-07-05T06:54:53.920863+00:00","updated_at":"2026-07-05T06:54:53.920863+00:00"}