{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KT4LHULRRSVHMGIUCCEZBUGX2M","short_pith_number":"pith:KT4LHULR","schema_version":"1.0","canonical_sha256":"54f8b3d1718caa761914108990d0d7d33ca68a9edf7b59a0b70ecd3b6044c868","source":{"kind":"arxiv","id":"2310.20025","version":3},"attestation_state":"computed","paper":{"title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Giovanni Montana, Hao Sun, Meng Fang, Mianchu Wang, Rui Yang, Xi Chen","submitted_at":"2023-10-30T21:19:52Z","abstract_excerpt":"Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face constraints in handling limited data and generalizing to unseen goals. In this work, we propose Goal-conditioned Offline Planning (GOPlan), a novel model-based framework that contains two key phases: (1) pretraining a prior policy capable of capturing multi-modal action distribution within the multi-goal dataset; (2) employing the reanalysis method with pla"},"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":"2310.20025","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-30T21:19:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1989cd2741588be20b2a05d234124350009190ab27de49648f11e0ceee3c04be","abstract_canon_sha256":"1b9379a41dcac3bb4774a777d3d3238920b7616082f2e0774db2502262660f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:37.867967Z","signature_b64":"bdl0LYz6dnZZRgURdewU1oRlDE2O+PZy3h3JySLBPXJKeSmNKj4Lom/t0mEp96tUl/7dRFNgpWixTG4TctDxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54f8b3d1718caa761914108990d0d7d33ca68a9edf7b59a0b70ecd3b6044c868","last_reissued_at":"2026-07-05T08:19:37.867436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:37.867436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Giovanni Montana, Hao Sun, Meng Fang, Mianchu Wang, Rui Yang, Xi Chen","submitted_at":"2023-10-30T21:19:52Z","abstract_excerpt":"Offline Goal-Conditioned RL (GCRL) offers a feasible paradigm for learning general-purpose policies from diverse and multi-task offline datasets. Despite notable recent progress, the predominant offline GCRL methods, mainly model-free, face constraints in handling limited data and generalizing to unseen goals. In this work, we propose Goal-conditioned Offline Planning (GOPlan), a novel model-based framework that contains two key phases: (1) pretraining a prior policy capable of capturing multi-modal action distribution within the multi-goal dataset; (2) employing the reanalysis method with pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20025","kind":"arxiv","version":3},"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/2310.20025/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":"2310.20025","created_at":"2026-07-05T08:19:37.867495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20025v3","created_at":"2026-07-05T08:19:37.867495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20025","created_at":"2026-07-05T08:19:37.867495+00:00"},{"alias_kind":"pith_short_12","alias_value":"KT4LHULRRSVH","created_at":"2026-07-05T08:19:37.867495+00:00"},{"alias_kind":"pith_short_16","alias_value":"KT4LHULRRSVHMGIU","created_at":"2026-07-05T08:19:37.867495+00:00"},{"alias_kind":"pith_short_8","alias_value":"KT4LHULR","created_at":"2026-07-05T08:19:37.867495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":147,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M","json":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M.json","graph_json":"https://pith.science/api/pith-number/KT4LHULRRSVHMGIUCCEZBUGX2M/graph.json","events_json":"https://pith.science/api/pith-number/KT4LHULRRSVHMGIUCCEZBUGX2M/events.json","paper":"https://pith.science/paper/KT4LHULR"},"agent_actions":{"view_html":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M","download_json":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M.json","view_paper":"https://pith.science/paper/KT4LHULR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20025&json=true","fetch_graph":"https://pith.science/api/pith-number/KT4LHULRRSVHMGIUCCEZBUGX2M/graph.json","fetch_events":"https://pith.science/api/pith-number/KT4LHULRRSVHMGIUCCEZBUGX2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M/action/storage_attestation","attest_author":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M/action/author_attestation","sign_citation":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M/action/citation_signature","submit_replication":"https://pith.science/pith/KT4LHULRRSVHMGIUCCEZBUGX2M/action/replication_record"}},"created_at":"2026-07-05T08:19:37.867495+00:00","updated_at":"2026-07-05T08:19:37.867495+00:00"}