{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AZLKUFJH2D74MPQZJR2ZWSUDAY","short_pith_number":"pith:AZLKUFJH","schema_version":"1.0","canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","source":{"kind":"arxiv","id":"2307.14993","version":2},"attestation_state":"computed","paper":{"title":"Thinker: Learning to Plan and Act","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Krueger, Ivan Anokhin, Stephen Chung","submitted_at":"2023-07-27T16:40:14Z","abstract_excerpt":"We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously"},"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":"2307.14993","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-07-27T16:40:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e7a4ed5e3fbce61b036f2995739b8cc8acf005a842b0d62f076acaa5ab600af","abstract_canon_sha256":"5c239d4ceed8aeeb6d7ac8b333c3b2388ea712eb8ea2d5d9781048bb59b76c4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:46.480366Z","signature_b64":"wds+O0Jz0cwNgu1WnRyXesrPRIdXq773P4+9B5IH2ZVPf9NXiwCfiXSHKm9yr612hNy4Jy/LKsdjReiWc7YwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0656aa1527d0ffc63e194c759b4a83063107dd62e14c8f4a281820602ecfbb57","last_reissued_at":"2026-07-05T07:05:46.479877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:46.479877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thinker: Learning to Plan and Act","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Krueger, Ivan Anokhin, Stephen Chung","submitted_at":"2023-07-27T16:40:14Z","abstract_excerpt":"We propose the Thinker algorithm, a novel approach that enables reinforcement learning agents to autonomously interact with and utilize a learned world model. The Thinker algorithm wraps the environment with a world model and introduces new actions designed for interacting with the world model. These model-interaction actions enable agents to perform planning by proposing alternative plans to the world model before selecting a final action to execute in the environment. This approach eliminates the need for handcrafted planning algorithms by enabling the agent to learn how to plan autonomously"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.14993","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/2307.14993/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":"2307.14993","created_at":"2026-07-05T07:05:46.479939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.14993v2","created_at":"2026-07-05T07:05:46.479939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.14993","created_at":"2026-07-05T07:05:46.479939+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZLKUFJH2D74","created_at":"2026-07-05T07:05:46.479939+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZLKUFJH2D74MPQZ","created_at":"2026-07-05T07:05:46.479939+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZLKUFJH","created_at":"2026-07-05T07:05:46.479939+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/AZLKUFJH2D74MPQZJR2ZWSUDAY","json":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY.json","graph_json":"https://pith.science/api/pith-number/AZLKUFJH2D74MPQZJR2ZWSUDAY/graph.json","events_json":"https://pith.science/api/pith-number/AZLKUFJH2D74MPQZJR2ZWSUDAY/events.json","paper":"https://pith.science/paper/AZLKUFJH"},"agent_actions":{"view_html":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY","download_json":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY.json","view_paper":"https://pith.science/paper/AZLKUFJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.14993&json=true","fetch_graph":"https://pith.science/api/pith-number/AZLKUFJH2D74MPQZJR2ZWSUDAY/graph.json","fetch_events":"https://pith.science/api/pith-number/AZLKUFJH2D74MPQZJR2ZWSUDAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/action/storage_attestation","attest_author":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/action/author_attestation","sign_citation":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/action/citation_signature","submit_replication":"https://pith.science/pith/AZLKUFJH2D74MPQZJR2ZWSUDAY/action/replication_record"}},"created_at":"2026-07-05T07:05:46.479939+00:00","updated_at":"2026-07-05T07:05:46.479939+00:00"}