{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AS5OSWX6VG5TKYT7HLY26NQVLO","short_pith_number":"pith:AS5OSWX6","schema_version":"1.0","canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","source":{"kind":"arxiv","id":"2406.02035","version":1},"attestation_state":"computed","paper":{"title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Guez, Bernardo Avila Pires, Clare Lyle, Diana Borsa, Khimya Khetarpal, Mark Rowland, Nicolas Heess, Will Dabney, Yunhao Tang, Zhaohan Daniel Guo","submitted_at":"2024-06-04T07:22:12Z","abstract_excerpt":"Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and dynamics model by bootstrapping from future latent representations (BYOL). Recent work has developed theoretical insights into these algorithms by studying a continuous-time ODE model for self-predictive representation learning under the simplifying assumption that the algorithm depends on a fixed policy (BYOL-$\\Pi$); this assumption is at odds with practical instantiations of such algorithms, which explicitly conditi"},"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":"2406.02035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T07:22:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eeb1729a8ecb1f88893fffa4387555639991904e41c4eb67b386cf05891dd80","abstract_canon_sha256":"d162d7ce9ce423898cb97749d275af1ef4e4af5e456307e1f83281b150638493"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:13.564009Z","signature_b64":"sy69a9JRxzOrUfjfselyFavPf2Ts/cvMw14G4mjfUicZV7BYAngKzC5s9sN9e0kk8ulTl9pvrlhyc/yyesQtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04bae95afea9bb35627f3af1af36155b97730ae7df92977287324dcea8034f60","last_reissued_at":"2026-07-05T08:27:13.563431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:13.563431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Guez, Bernardo Avila Pires, Clare Lyle, Diana Borsa, Khimya Khetarpal, Mark Rowland, Nicolas Heess, Will Dabney, Yunhao Tang, Zhaohan Daniel Guo","submitted_at":"2024-06-04T07:22:12Z","abstract_excerpt":"Learning a good representation is a crucial challenge for Reinforcement Learning (RL) agents. Self-predictive learning provides means to jointly learn a latent representation and dynamics model by bootstrapping from future latent representations (BYOL). Recent work has developed theoretical insights into these algorithms by studying a continuous-time ODE model for self-predictive representation learning under the simplifying assumption that the algorithm depends on a fixed policy (BYOL-$\\Pi$); this assumption is at odds with practical instantiations of such algorithms, which explicitly conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02035","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/2406.02035/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":"2406.02035","created_at":"2026-07-05T08:27:13.563494+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02035v1","created_at":"2026-07-05T08:27:13.563494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02035","created_at":"2026-07-05T08:27:13.563494+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS5OSWX6VG5T","created_at":"2026-07-05T08:27:13.563494+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS5OSWX6VG5TKYT7","created_at":"2026-07-05T08:27:13.563494+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS5OSWX6","created_at":"2026-07-05T08:27:13.563494+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17518","citing_title":"A Survey of State Representation Learning for Deep Reinforcement Learning","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO","json":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO.json","graph_json":"https://pith.science/api/pith-number/AS5OSWX6VG5TKYT7HLY26NQVLO/graph.json","events_json":"https://pith.science/api/pith-number/AS5OSWX6VG5TKYT7HLY26NQVLO/events.json","paper":"https://pith.science/paper/AS5OSWX6"},"agent_actions":{"view_html":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO","download_json":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO.json","view_paper":"https://pith.science/paper/AS5OSWX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02035&json=true","fetch_graph":"https://pith.science/api/pith-number/AS5OSWX6VG5TKYT7HLY26NQVLO/graph.json","fetch_events":"https://pith.science/api/pith-number/AS5OSWX6VG5TKYT7HLY26NQVLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/action/storage_attestation","attest_author":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/action/author_attestation","sign_citation":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/action/citation_signature","submit_replication":"https://pith.science/pith/AS5OSWX6VG5TKYT7HLY26NQVLO/action/replication_record"}},"created_at":"2026-07-05T08:27:13.563494+00:00","updated_at":"2026-07-05T08:27:13.563494+00:00"}