{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ANXLC7OYMD7WL23JZLYGGM4OI4","short_pith_number":"pith:ANXLC7OY","schema_version":"1.0","canonical_sha256":"036eb17dd860ff65eb69caf063338e4728ebad412c616ad246b939b9eaa58540","source":{"kind":"arxiv","id":"2206.11396","version":2},"attestation_state":"computed","paper":{"title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Sch\\\"afer, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2022-06-22T21:50:07Z","abstract_excerpt":"Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions, which may cause learning inefficiencies if important environmental changes take many steps to manifest. We propose Hierarchical $k$-Step Latent (HKSL), an auxiliary task that learns multiple representations via a hierarchy of forward models that learn to co"},"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":"2206.11396","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-22T21:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"8ba50373366786ad57de57f6bc8b450056821afc7726680f7743edf95828388c","abstract_canon_sha256":"02ad37e44844c155d9f3502441331d97823051eb22e2f3ff4e6b5d76d4bb14fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:24.328980Z","signature_b64":"Y1UheSCpMHS3XY3zxZe4218ooC2lP3fnqPg3X9DEmhiVTrlpaHloJOk+3IiWhxZlWc3MXSEKZ+KR/ASbmKJLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"036eb17dd860ff65eb69caf063338e4728ebad412c616ad246b939b9eaa58540","last_reissued_at":"2026-07-05T07:38:24.328392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:24.328392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Horizon Representations with Hierarchical Forward Models for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lukas Sch\\\"afer, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2022-06-22T21:50:07Z","abstract_excerpt":"Learning control from pixels is difficult for reinforcement learning (RL) agents because representation learning and policy learning are intertwined. Previous approaches remedy this issue with auxiliary representation learning tasks, but they either do not consider the temporal aspect of the problem or only consider single-step transitions, which may cause learning inefficiencies if important environmental changes take many steps to manifest. We propose Hierarchical $k$-Step Latent (HKSL), an auxiliary task that learns multiple representations via a hierarchy of forward models that learn to co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.11396","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/2206.11396/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":"2206.11396","created_at":"2026-07-05T07:38:24.328474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.11396v2","created_at":"2026-07-05T07:38:24.328474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.11396","created_at":"2026-07-05T07:38:24.328474+00:00"},{"alias_kind":"pith_short_12","alias_value":"ANXLC7OYMD7W","created_at":"2026-07-05T07:38:24.328474+00:00"},{"alias_kind":"pith_short_16","alias_value":"ANXLC7OYMD7WL23J","created_at":"2026-07-05T07:38:24.328474+00:00"},{"alias_kind":"pith_short_8","alias_value":"ANXLC7OY","created_at":"2026-07-05T07:38:24.328474+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/ANXLC7OYMD7WL23JZLYGGM4OI4","json":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4.json","graph_json":"https://pith.science/api/pith-number/ANXLC7OYMD7WL23JZLYGGM4OI4/graph.json","events_json":"https://pith.science/api/pith-number/ANXLC7OYMD7WL23JZLYGGM4OI4/events.json","paper":"https://pith.science/paper/ANXLC7OY"},"agent_actions":{"view_html":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4","download_json":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4.json","view_paper":"https://pith.science/paper/ANXLC7OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.11396&json=true","fetch_graph":"https://pith.science/api/pith-number/ANXLC7OYMD7WL23JZLYGGM4OI4/graph.json","fetch_events":"https://pith.science/api/pith-number/ANXLC7OYMD7WL23JZLYGGM4OI4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4/action/storage_attestation","attest_author":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4/action/author_attestation","sign_citation":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4/action/citation_signature","submit_replication":"https://pith.science/pith/ANXLC7OYMD7WL23JZLYGGM4OI4/action/replication_record"}},"created_at":"2026-07-05T07:38:24.328474+00:00","updated_at":"2026-07-05T07:38:24.328474+00:00"}