{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5IMNTGCPCOPPMZ36753LOFQIYH","short_pith_number":"pith:5IMNTGCP","schema_version":"1.0","canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","source":{"kind":"arxiv","id":"2605.13207","version":1},"attestation_state":"computed","paper":{"title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Proutiere, Stefan Stojanovic","submitted_at":"2026-05-13T08:58:33Z","abstract_excerpt":"Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manua"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.13207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:58:33Z","cross_cats_sorted":[],"title_canon_sha256":"09f2085250a3244c76dfc64a56592c9b2f11523a3a97982b0ab1af7245936e21","abstract_canon_sha256":"eb236112774df187358ca124604368097ee047bca5ed54dd1318152a31c2821a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:48.588045Z","signature_b64":"NutoZgjLl8aGWKcGqRv6UESiHjTjFm3vPJJmF0O7LsOsl2v7j3tkSfK1xdYRBOyVs5xmK0N6aWa0tTFQAjnaDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea18d9984f139ef6677eff76b71608c1ef188d712c6ea0e74f1e87623ddfb6c4","last_reissued_at":"2026-05-18T03:08:48.587295Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:48.587295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Switching Successor Measures for Hierarchical Zero-shot Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Proutiere, Stefan Stojanovic","submitted_at":"2026-05-13T08:58:33Z","abstract_excerpt":"Hierarchical reinforcement learning can improve generalization by decomposing long-horizon decision-making into simpler subproblems. However, existing approaches often rely on restrictive design choices, such as fixed temporal abstractions or goal-conditioned objectives, which largely confine them to goal-reaching tasks and limit their applicability to general reward functions. In this paper, we introduce switching successor measures, an extension of successor measures that enables hierarchical control in zero-shot reinforcement learning without additional supervision, fixed horizons, or manua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0bda80f9832fa6543a6f09680df36d3a17fe87b5ec8a6b1857d6edc24bcc995b"},"source":{"id":"2605.13207","kind":"arxiv","version":1},"verdict":{"id":"f4c4fbb0-0e27-49fc-a8e2-0277f5c3967f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:23:39.992215Z","strongest_claim":"Switching successor measures arise naturally from classical successor measures while preserving their underlying structure, allowing FB π-Switch to extract both a high-level subgoal-selection policy and a low-level control policy directly from forward-backward representations for hierarchical zero-shot RL without additional supervision, fixed horizons, or manually designed subgoals.","one_line_summary":"Switching successor measures extend classical successor measures to enable hierarchical zero-shot RL via the FB π-Switch algorithm that extracts subgoal-selection and control policies from forward-backward representations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That switching successor measures can be derived from classical ones in a way that preserves structure sufficiently to support emergent hierarchical behavior from a single FB representation across both goal-conditioned and general reward tasks.","pith_extraction_headline":"Switching successor measures arise naturally from classical ones and let a single forward-backward representation produce both high-level subgoals and low-level actions in zero-shot hierarchical RL."},"references":{"count":64,"sample":[{"doi":"","year":2021,"title":"Deep reinforcement learning at the edge of the statistical precipice","work_id":"c3d48de0-debb-4594-8d88-4bbd76ba95ee","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"A unified framework for unsupervised reinforcement learning al- gorithms","work_id":"599e9445-4bfe-4ead-9512-2ab76ede8723","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Proto successor measure: Representing the behavior space of an RL agent.arXiv preprint arXiv:2411.19418, 2024","work_id":"e2101019-a668-4daf-be2d-55e515f58012","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Option-aware temporally abstracted value for offline goal-conditioned reinforcement learning","work_id":"178e6002-05c1-4b61-838e-d8e5477a8d7c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"OPAL: Offline primitive discovery for accelerating offline reinforcement learning","work_id":"286b3006-aac9-45e5-bec8-8122a192c114","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":64,"snapshot_sha256":"d827bc72f2d7a74a477eb500d5465e590674be9d1ffa73c3a7267c0f8e18c273","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"461adf71a93f3a186bf64f09d8638da67f16902012ca9553c18b810495f73e45"},"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":"2605.13207","created_at":"2026-05-18T03:08:48.587428+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13207v1","created_at":"2026-05-18T03:08:48.587428+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13207","created_at":"2026-05-18T03:08:48.587428+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IMNTGCPCOPP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IMNTGCPCOPPMZ36","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IMNTGCP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH","json":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH.json","graph_json":"https://pith.science/api/pith-number/5IMNTGCPCOPPMZ36753LOFQIYH/graph.json","events_json":"https://pith.science/api/pith-number/5IMNTGCPCOPPMZ36753LOFQIYH/events.json","paper":"https://pith.science/paper/5IMNTGCP"},"agent_actions":{"view_html":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH","download_json":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH.json","view_paper":"https://pith.science/paper/5IMNTGCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13207&json=true","fetch_graph":"https://pith.science/api/pith-number/5IMNTGCPCOPPMZ36753LOFQIYH/graph.json","fetch_events":"https://pith.science/api/pith-number/5IMNTGCPCOPPMZ36753LOFQIYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/action/storage_attestation","attest_author":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/action/author_attestation","sign_citation":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/action/citation_signature","submit_replication":"https://pith.science/pith/5IMNTGCPCOPPMZ36753LOFQIYH/action/replication_record"}},"created_at":"2026-05-18T03:08:48.587428+00:00","updated_at":"2026-05-18T03:08:48.587428+00:00"}