{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:AZJAQCMLQYOZ5NHXWF7RLFNR6G","short_pith_number":"pith:AZJAQCML","schema_version":"1.0","canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","source":{"kind":"arxiv","id":"1809.09318","version":4},"attestation_state":"computed","paper":{"title":"Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason J. Corso, Jeffrey M. Siskind, Shurjo Banerjee, Vikas Dhiman","submitted_at":"2018-09-25T05:09:32Z","abstract_excerpt":"Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations. Model-free RL struggles to transfer learned information when the goal location changes, but achieves high asymptotic accuracy in single goal tasks. Model-based RL can transfer learned information to new goal locations by retaining the explicitly learned state-dynamics, but is li"},"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":"1809.09318","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T05:09:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c6330fe1f62620baabe249ae97f70e9ba1a93eca3ee17b9988b92247d61ab119","abstract_canon_sha256":"0d13e4bb3a6bc594b055ee800851c4474d107a7d5f232ab1530e3b08b6543d8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:52.865375Z","signature_b64":"yQob0aIB75Bh69saH0t7bvp81rjCevvZVuuC7axWJJ3AatgnUjWgPJwDVdJZ+ps0tKv6p3iocWuzVxz34FtoAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","last_reissued_at":"2026-05-17T23:56:52.864970Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:52.864970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason J. Corso, Jeffrey M. Siskind, Shurjo Banerjee, Vikas Dhiman","submitted_at":"2018-09-25T05:09:32Z","abstract_excerpt":"Consider mutli-goal tasks that involve static environments and dynamic goals. Examples of such tasks, such as goal-directed navigation and pick-and-place in robotics, abound. Two types of Reinforcement Learning (RL) algorithms are used for such tasks: model-free or model-based. Each of these approaches has limitations. Model-free RL struggles to transfer learned information when the goal location changes, but achieves high asymptotic accuracy in single goal tasks. Model-based RL can transfer learned information to new goal locations by retaining the explicitly learned state-dynamics, but is li"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09318","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1809.09318","created_at":"2026-05-17T23:56:52.865028+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09318v4","created_at":"2026-05-17T23:56:52.865028+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09318","created_at":"2026-05-17T23:56:52.865028+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZJAQCMLQYOZ","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZJAQCMLQYOZ5NHX","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZJAQCML","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":220,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G","json":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G.json","graph_json":"https://pith.science/api/pith-number/AZJAQCMLQYOZ5NHXWF7RLFNR6G/graph.json","events_json":"https://pith.science/api/pith-number/AZJAQCMLQYOZ5NHXWF7RLFNR6G/events.json","paper":"https://pith.science/paper/AZJAQCML"},"agent_actions":{"view_html":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G","download_json":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G.json","view_paper":"https://pith.science/paper/AZJAQCML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09318&json=true","fetch_graph":"https://pith.science/api/pith-number/AZJAQCMLQYOZ5NHXWF7RLFNR6G/graph.json","fetch_events":"https://pith.science/api/pith-number/AZJAQCMLQYOZ5NHXWF7RLFNR6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/action/storage_attestation","attest_author":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/action/author_attestation","sign_citation":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/action/citation_signature","submit_replication":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/action/replication_record"}},"created_at":"2026-05-17T23:56:52.865028+00:00","updated_at":"2026-05-17T23:56:52.865028+00:00"}