{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2A4A3FIM4SNIVXUBFTD4C56MNC","short_pith_number":"pith:2A4A3FIM","canonical_record":{"source":{"id":"1902.00843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T04:44:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b61145322a0fe471053101f9471bcbbe595ecd2beb6b4f03de586287bad6141","abstract_canon_sha256":"e4abb1222f28830dd7a1c8233c5061be2c412ff7a75f23d921ee4adcbf25092d"},"schema_version":"1.0"},"canonical_sha256":"d0380d950ce49a8ade812cc7c177cc68ac71347405fa5a29261d9258e60079ba","source":{"kind":"arxiv","id":"1902.00843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00843","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00843v1","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00843","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"pith_short_12","alias_value":"2A4A3FIM4SNI","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2A4A3FIM4SNIVXUB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2A4A3FIM","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2A4A3FIM4SNIVXUBFTD4C56MNC","target":"record","payload":{"canonical_record":{"source":{"id":"1902.00843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T04:44:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b61145322a0fe471053101f9471bcbbe595ecd2beb6b4f03de586287bad6141","abstract_canon_sha256":"e4abb1222f28830dd7a1c8233c5061be2c412ff7a75f23d921ee4adcbf25092d"},"schema_version":"1.0"},"canonical_sha256":"d0380d950ce49a8ade812cc7c177cc68ac71347405fa5a29261d9258e60079ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:51.992197Z","signature_b64":"ijgROZ4p4aC1siPshkf1yYNMC/VTB9FZq0FcxyGPzE9P631S8mfbDScuoTNqb3Fv1RR1OHivBKHHIKtbfPysAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0380d950ce49a8ade812cc7c177cc68ac71347405fa5a29261d9258e60079ba","last_reissued_at":"2026-05-17T23:54:51.991753Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:51.991753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.00843","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:54:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d9yLYSyGSdd+CCNt2vlMKzUvyXa4GOzDRE5oT889KCyXrR3tCBWVUM/TXfgVrX8IDrQkO8tpoWxFmz3iP7zEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:17:09.793626Z"},"content_sha256":"767532b184b38dfcb23a513a513fc3ae4d6c93fdd20329bfb71480e7d71ea127","schema_version":"1.0","event_id":"sha256:767532b184b38dfcb23a513a513fc3ae4d6c93fdd20329bfb71480e7d71ea127"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2A4A3FIM4SNIVXUBFTD4C56MNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Francisco M. Garcia, Philip S. Thomas","submitted_at":"2019-02-03T04:44:11Z","abstract_excerpt":"In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience with similar problems can provide an agent with information about how it should explore when facing a new but related problem. We show that the search for an optimal exploration strategy can be formulated as a reinforcement learning problem itself and demonstrate that such strat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00843","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":""},"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":"2026-05-17T23:54:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pafF2+1QuiEkDc9Lq/AKp4jc1q7m3w9W5v2IgZmxdH1r4GyOF1j0RC5jr9ZWXvRLJDaz0kPlFfRpm9Wkivi+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T19:17:09.794301Z"},"content_sha256":"a718c6f51cc1e312dea4d7f105594d02d2301789b7e88f9e361ab6ffa95cfdb4","schema_version":"1.0","event_id":"sha256:a718c6f51cc1e312dea4d7f105594d02d2301789b7e88f9e361ab6ffa95cfdb4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/bundle.json","state_url":"https://pith.science/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/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":"2026-06-06T19:17:09Z","links":{"resolver":"https://pith.science/pith/2A4A3FIM4SNIVXUBFTD4C56MNC","bundle":"https://pith.science/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/bundle.json","state":"https://pith.science/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2A4A3FIM4SNIVXUBFTD4C56MNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2A4A3FIM4SNIVXUBFTD4C56MNC","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":"e4abb1222f28830dd7a1c8233c5061be2c412ff7a75f23d921ee4adcbf25092d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T04:44:11Z","title_canon_sha256":"5b61145322a0fe471053101f9471bcbbe595ecd2beb6b4f03de586287bad6141"},"schema_version":"1.0","source":{"id":"1902.00843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.00843","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"arxiv_version","alias_value":"1902.00843v1","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.00843","created_at":"2026-05-17T23:54:51Z"},{"alias_kind":"pith_short_12","alias_value":"2A4A3FIM4SNI","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"2A4A3FIM4SNIVXUB","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"2A4A3FIM","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:a718c6f51cc1e312dea4d7f105594d02d2301789b7e88f9e361ab6ffa95cfdb4","target":"graph","created_at":"2026-05-17T23:54:51Z","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":"In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience with similar problems can provide an agent with information about how it should explore when facing a new but related problem. We show that the search for an optimal exploration strategy can be formulated as a reinforcement learning problem itself and demonstrate that such strat","authors_text":"Francisco M. Garcia, Philip S. Thomas","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T04:44:11Z","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.00843","kind":"arxiv","version":1},"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":"sha256:767532b184b38dfcb23a513a513fc3ae4d6c93fdd20329bfb71480e7d71ea127","target":"record","created_at":"2026-05-17T23:54:51Z","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":"e4abb1222f28830dd7a1c8233c5061be2c412ff7a75f23d921ee4adcbf25092d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-03T04:44:11Z","title_canon_sha256":"5b61145322a0fe471053101f9471bcbbe595ecd2beb6b4f03de586287bad6141"},"schema_version":"1.0","source":{"id":"1902.00843","kind":"arxiv","version":1}},"canonical_sha256":"d0380d950ce49a8ade812cc7c177cc68ac71347405fa5a29261d9258e60079ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0380d950ce49a8ade812cc7c177cc68ac71347405fa5a29261d9258e60079ba","first_computed_at":"2026-05-17T23:54:51.991753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:51.991753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ijgROZ4p4aC1siPshkf1yYNMC/VTB9FZq0FcxyGPzE9P631S8mfbDScuoTNqb3Fv1RR1OHivBKHHIKtbfPysAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:51.992197Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.00843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:767532b184b38dfcb23a513a513fc3ae4d6c93fdd20329bfb71480e7d71ea127","sha256:a718c6f51cc1e312dea4d7f105594d02d2301789b7e88f9e361ab6ffa95cfdb4"],"state_sha256":"5828064982b65c8db0d9701744c84e10abe648b0e80ab0646c5f6e1fd7bb7d0b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2IYthKt1itxMR3e+GHsv6iISXaRyECrrnMzSD4fVULd2VLLVuVivBS73Mo1t3gHxYZN+sFKQ1IahGfEMmNMVAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T19:17:09.798224Z","bundle_sha256":"330860e2e836dfbd65c618c225515e8ef08a9e3d872020cf4dd9f3a10d2fa63e"}}