{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:46UPRXGMQFTBIAENAQOFOSV3WG","short_pith_number":"pith:46UPRXGM","schema_version":"1.0","canonical_sha256":"e7a8f8dccc816614008d041c574abbb1852b5aeceb077648225bfe4648508bc0","source":{"kind":"arxiv","id":"1907.00884","version":1},"attestation_state":"computed","paper":{"title":"On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nick Denis","submitted_at":"2019-07-01T15:56:24Z","abstract_excerpt":"Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we introduce two metrics on the state space that encode notions of traversibility of the state space for an agent. Using these metrics a topological covering is constructed by way of a set of landmark states in a fully self-supervised manner. We show that these landmark coverings con"},"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":"1907.00884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-01T15:56:24Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c18300851b0fff31e3d5850027708d8b87b062c2425227d43d3d3299e29a1288","abstract_canon_sha256":"86c674141793cf3f4713f9df2c8c38c41a3b788cfce2c51330f466d271a9c20c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:47.737107Z","signature_b64":"090KHf1ppTEWoI410dzRETfKcSIvca0r63NmisCDQciwdN23wWYq5r10WDFkliwbugBXN5WlEvec5WbNKEFfBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7a8f8dccc816614008d041c574abbb1852b5aeceb077648225bfe4648508bc0","last_reissued_at":"2026-05-17T23:41:47.736471Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:47.736471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On mechanisms for transfer using landmark value functions in multi-task lifelong reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Nick Denis","submitted_at":"2019-07-01T15:56:24Z","abstract_excerpt":"Transfer learning across different reinforcement learning (RL) tasks is becoming an increasingly valuable area of research. We consider a goal-based multi-task RL framework and mechanisms by which previously solved tasks can reduce sample complexity and regret when the agent is faced with a new task. Specifically, we introduce two metrics on the state space that encode notions of traversibility of the state space for an agent. Using these metrics a topological covering is constructed by way of a set of landmark states in a fully self-supervised manner. We show that these landmark coverings con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00884","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1907.00884","created_at":"2026-05-17T23:41:47.736567+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00884v1","created_at":"2026-05-17T23:41:47.736567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00884","created_at":"2026-05-17T23:41:47.736567+00:00"},{"alias_kind":"pith_short_12","alias_value":"46UPRXGMQFTB","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"46UPRXGMQFTBIAEN","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"46UPRXGM","created_at":"2026-05-18T12:33:10.108867+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/46UPRXGMQFTBIAENAQOFOSV3WG","json":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG.json","graph_json":"https://pith.science/api/pith-number/46UPRXGMQFTBIAENAQOFOSV3WG/graph.json","events_json":"https://pith.science/api/pith-number/46UPRXGMQFTBIAENAQOFOSV3WG/events.json","paper":"https://pith.science/paper/46UPRXGM"},"agent_actions":{"view_html":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG","download_json":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG.json","view_paper":"https://pith.science/paper/46UPRXGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00884&json=true","fetch_graph":"https://pith.science/api/pith-number/46UPRXGMQFTBIAENAQOFOSV3WG/graph.json","fetch_events":"https://pith.science/api/pith-number/46UPRXGMQFTBIAENAQOFOSV3WG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG/action/storage_attestation","attest_author":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG/action/author_attestation","sign_citation":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG/action/citation_signature","submit_replication":"https://pith.science/pith/46UPRXGMQFTBIAENAQOFOSV3WG/action/replication_record"}},"created_at":"2026-05-17T23:41:47.736567+00:00","updated_at":"2026-05-17T23:41:47.736567+00:00"}