{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNWSYLAC2ULR5RZSEZ5IB7EHJK","short_pith_number":"pith:HNWSYLAC","schema_version":"1.0","canonical_sha256":"3b6d2c2c02d5171ec732267a80fc874ab6cf9d1738ed0f9094b75bd9f01edf06","source":{"kind":"arxiv","id":"2411.10809","version":1},"attestation_state":"computed","paper":{"title":"Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cong Guan, Feng Chen, Fuguang Han, Lei Yuan, Yang Yu, Zhilong Zhang, Zongzhang Zhang","submitted_at":"2024-11-16T14:03:23Z","abstract_excerpt":"Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this problem setting, a pivotal challenge revolves around \\textit{catastrophic forgetting} issue, wherein the agent is prone to effortlessly erode the decisional knowledge associated with past encountered tasks when learning the new one. In recent progresses, the \\textit{generative replay} methods have showcased substantial potential by employing generative models t"},"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":"2411.10809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-16T14:03:23Z","cross_cats_sorted":[],"title_canon_sha256":"b653cdb652ef849d19fa8936dca293949ea0572da52dc77a6aad2c82924319d5","abstract_canon_sha256":"1fa57b01927db188fed8ed96e00912cc876895853053088a0115e76e7562d2b8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:22.520271Z","signature_b64":"t3uxqBlAgZqhSWt9GsR3xaJR0Hkn0ZD/r59qJjznYBW+m8gb2ebDoH7zdumr8yoZHeMzBFTI2Pwcg8icqobxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b6d2c2c02d5171ec732267a80fc874ab6cf9d1738ed0f9094b75bd9f01edf06","last_reissued_at":"2026-07-05T09:36:22.519806Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:22.519806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cong Guan, Feng Chen, Fuguang Han, Lei Yuan, Yang Yu, Zhilong Zhang, Zongzhang Zhang","submitted_at":"2024-11-16T14:03:23Z","abstract_excerpt":"Given the inherent non-stationarity prevalent in real-world applications, continual Reinforcement Learning (RL) aims to equip the agent with the capability to address a series of sequentially presented decision-making tasks. Within this problem setting, a pivotal challenge revolves around \\textit{catastrophic forgetting} issue, wherein the agent is prone to effortlessly erode the decisional knowledge associated with past encountered tasks when learning the new one. In recent progresses, the \\textit{generative replay} methods have showcased substantial potential by employing generative models t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.10809","kind":"arxiv","version":1},"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/2411.10809/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":"2411.10809","created_at":"2026-07-05T09:36:22.519854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.10809v1","created_at":"2026-07-05T09:36:22.519854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.10809","created_at":"2026-07-05T09:36:22.519854+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNWSYLAC2ULR","created_at":"2026-07-05T09:36:22.519854+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNWSYLAC2ULR5RZS","created_at":"2026-07-05T09:36:22.519854+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNWSYLAC","created_at":"2026-07-05T09:36:22.519854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25389","citing_title":"Offline Multi-agent Continual Cooperation via Skill Partition and Reuse","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08102","citing_title":"Continual Quadruped Robots Coordination via Semantic Skill Discovery","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK","json":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK.json","graph_json":"https://pith.science/api/pith-number/HNWSYLAC2ULR5RZSEZ5IB7EHJK/graph.json","events_json":"https://pith.science/api/pith-number/HNWSYLAC2ULR5RZSEZ5IB7EHJK/events.json","paper":"https://pith.science/paper/HNWSYLAC"},"agent_actions":{"view_html":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK","download_json":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK.json","view_paper":"https://pith.science/paper/HNWSYLAC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.10809&json=true","fetch_graph":"https://pith.science/api/pith-number/HNWSYLAC2ULR5RZSEZ5IB7EHJK/graph.json","fetch_events":"https://pith.science/api/pith-number/HNWSYLAC2ULR5RZSEZ5IB7EHJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK/action/storage_attestation","attest_author":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK/action/author_attestation","sign_citation":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK/action/citation_signature","submit_replication":"https://pith.science/pith/HNWSYLAC2ULR5RZSEZ5IB7EHJK/action/replication_record"}},"created_at":"2026-07-05T09:36:22.519854+00:00","updated_at":"2026-07-05T09:36:22.519854+00:00"}