{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DWTHHOPRO6UHEZD7LUGOL66ZMA","short_pith_number":"pith:DWTHHOPR","schema_version":"1.0","canonical_sha256":"1da673b9f177a872647f5d0ce5fbd9602e0d5e2e46bb90c71d2e8a09c6285811","source":{"kind":"arxiv","id":"2302.02182","version":4},"attestation_state":"computed","paper":{"title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arash Nasr-Esfahany, Malte Schwarzkopf, Mohammad Alizadeh, Pouya Hamadanian, Siddartha Sen","submitted_at":"2023-02-04T15:31:19Z","abstract_excerpt":"We study online reinforcement learning (RL) in non-stationary environments, where a time-varying exogenous context process affects the environment dynamics. Online RL is challenging in such environments due to \"catastrophic forgetting\" (CF). The agent tends to forget prior knowledge as it trains on new experiences. Prior approaches to mitigate this issue assume task labels (which are often not available in practice), employ brittle regularization heuristics, or use off-policy methods that suffer from instability and poor performance.\n  We present Locally Constrained Policy Optimization (LCPO),"},"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":"2302.02182","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T15:31:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bc871371c019269497d218b3ba8faa04d18a6fce3d45fb66c328006e8ecb6f7","abstract_canon_sha256":"2a9e1f546b2966c3110aa6c214c4423b4d8b35d13cbdccbcb8bfffeced9f3593"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:43.947065Z","signature_b64":"f+XraiVOkog5ew5Ov7WQpqUxuEgQxwFtX+Rq1s8Ps7O5FEL2NdE8ZNV4WCDW62XKO1eta6Kz9l8qd3ik/7nEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1da673b9f177a872647f5d0ce5fbd9602e0d5e2e46bb90c71d2e8a09c6285811","last_reissued_at":"2026-07-05T10:41:43.946567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:43.946567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Reinforcement Learning in Non-Stationary Context-Driven Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arash Nasr-Esfahany, Malte Schwarzkopf, Mohammad Alizadeh, Pouya Hamadanian, Siddartha Sen","submitted_at":"2023-02-04T15:31:19Z","abstract_excerpt":"We study online reinforcement learning (RL) in non-stationary environments, where a time-varying exogenous context process affects the environment dynamics. Online RL is challenging in such environments due to \"catastrophic forgetting\" (CF). The agent tends to forget prior knowledge as it trains on new experiences. Prior approaches to mitigate this issue assume task labels (which are often not available in practice), employ brittle regularization heuristics, or use off-policy methods that suffer from instability and poor performance.\n  We present Locally Constrained Policy Optimization (LCPO),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02182","kind":"arxiv","version":4},"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/2302.02182/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":"2302.02182","created_at":"2026-07-05T10:41:43.946632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02182v4","created_at":"2026-07-05T10:41:43.946632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02182","created_at":"2026-07-05T10:41:43.946632+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWTHHOPRO6UH","created_at":"2026-07-05T10:41:43.946632+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWTHHOPRO6UHEZD7","created_at":"2026-07-05T10:41:43.946632+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWTHHOPR","created_at":"2026-07-05T10:41:43.946632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18026","citing_title":"RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02495","citing_title":"Efficient Preference Poisoning Attack on Offline RLHF","ref_index":94,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA","json":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA.json","graph_json":"https://pith.science/api/pith-number/DWTHHOPRO6UHEZD7LUGOL66ZMA/graph.json","events_json":"https://pith.science/api/pith-number/DWTHHOPRO6UHEZD7LUGOL66ZMA/events.json","paper":"https://pith.science/paper/DWTHHOPR"},"agent_actions":{"view_html":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA","download_json":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA.json","view_paper":"https://pith.science/paper/DWTHHOPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02182&json=true","fetch_graph":"https://pith.science/api/pith-number/DWTHHOPRO6UHEZD7LUGOL66ZMA/graph.json","fetch_events":"https://pith.science/api/pith-number/DWTHHOPRO6UHEZD7LUGOL66ZMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA/action/storage_attestation","attest_author":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA/action/author_attestation","sign_citation":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA/action/citation_signature","submit_replication":"https://pith.science/pith/DWTHHOPRO6UHEZD7LUGOL66ZMA/action/replication_record"}},"created_at":"2026-07-05T10:41:43.946632+00:00","updated_at":"2026-07-05T10:41:43.946632+00:00"}