{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:AZJAQCMLQYOZ5NHXWF7RLFNR6G","short_pith_number":"pith:AZJAQCML","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"},"canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","source":{"kind":"arxiv","id":"1809.09318","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09318","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09318v4","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09318","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"AZJAQCMLQYOZ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AZJAQCMLQYOZ5NHX","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AZJAQCML","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:AZJAQCMLQYOZ5NHXWF7RLFNR6G","target":"record","payload":{"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"},"canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","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"},"source_kind":"arxiv","source_id":"1809.09318","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALrHC6/Mr9hnhPG6W5zf5h5qCO6CgPAnoTZkdgcN6o1ITXMt3VDma/vDzkLWRh/0YVD8siwOMPVUsX6GG39JDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:21:03.459504Z"},"content_sha256":"4be11d54a57517e190daac9beda7ce5e7b52e77f2d19807b0ea4d4ac0ef90467","schema_version":"1.0","event_id":"sha256:4be11d54a57517e190daac9beda7ce5e7b52e77f2d19807b0ea4d4ac0ef90467"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:AZJAQCMLQYOZ5NHXWF7RLFNR6G","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ktN2asSs9n6R1cz7ZKAUu9ixmgO7lVYhnE09AiR0a5Ukuv/5ybIHsRXILemkBdP/UfjBCJTkpONkby9eftLDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:21:03.460193Z"},"content_sha256":"6cddeb98da3f9c60ba14037540c17908c9688f89449effb6d662786774a135d5","schema_version":"1.0","event_id":"sha256:6cddeb98da3f9c60ba14037540c17908c9688f89449effb6d662786774a135d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/bundle.json","state_url":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T11:21:03Z","links":{"resolver":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G","bundle":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/bundle.json","state":"https://pith.science/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZJAQCMLQYOZ5NHXWF7RLFNR6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:AZJAQCMLQYOZ5NHXWF7RLFNR6G","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0d13e4bb3a6bc594b055ee800851c4474d107a7d5f232ab1530e3b08b6543d8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T05:09:32Z","title_canon_sha256":"c6330fe1f62620baabe249ae97f70e9ba1a93eca3ee17b9988b92247d61ab119"},"schema_version":"1.0","source":{"id":"1809.09318","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.09318","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"arxiv_version","alias_value":"1809.09318v4","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09318","created_at":"2026-05-17T23:56:52Z"},{"alias_kind":"pith_short_12","alias_value":"AZJAQCMLQYOZ","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"AZJAQCMLQYOZ5NHX","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"AZJAQCML","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:6cddeb98da3f9c60ba14037540c17908c9688f89449effb6d662786774a135d5","target":"graph","created_at":"2026-05-17T23:56:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Jason J. Corso, Jeffrey M. Siskind, Shurjo Banerjee, Vikas Dhiman","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T05:09:32Z","title":"Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09318","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4be11d54a57517e190daac9beda7ce5e7b52e77f2d19807b0ea4d4ac0ef90467","target":"record","created_at":"2026-05-17T23:56:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0d13e4bb3a6bc594b055ee800851c4474d107a7d5f232ab1530e3b08b6543d8a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T05:09:32Z","title_canon_sha256":"c6330fe1f62620baabe249ae97f70e9ba1a93eca3ee17b9988b92247d61ab119"},"schema_version":"1.0","source":{"id":"1809.09318","kind":"arxiv","version":4}},"canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065208098b861d9eb4f7b17f1595b1f1b5836ec3a92fb4e91b7619b29ba18010","first_computed_at":"2026-05-17T23:56:52.864970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:52.864970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yQob0aIB75Bh69saH0t7bvp81rjCevvZVuuC7axWJJ3AatgnUjWgPJwDVdJZ+ps0tKv6p3iocWuzVxz34FtoAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:52.865375Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.09318","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4be11d54a57517e190daac9beda7ce5e7b52e77f2d19807b0ea4d4ac0ef90467","sha256:6cddeb98da3f9c60ba14037540c17908c9688f89449effb6d662786774a135d5"],"state_sha256":"555bfc8b736746521eb89cfa19de716cf0a822b7196a799bd424537799b41db6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CK5pCVs7PyqlnJxmSc9CiyC6zFdwsYSR5YIyyjTOtAB8ETP3OEY5LP5DrIdf4/S6Mz31VS8hWvjO8ZdMfjRFBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:21:03.463807Z","bundle_sha256":"ef7d461c04ed6eb24b0fc7e44c1b5d1ca8b4cd5817445dfa1374fa44d920a607"}}