{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:JXTWD5RQHF4LSAXC3F3ET2Z5BX","short_pith_number":"pith:JXTWD5RQ","schema_version":"1.0","canonical_sha256":"4de761f6303978b902e2d97649eb3d0dc477fa9e276f484ed0ce26fbbe9ecb32","source":{"kind":"arxiv","id":"1511.08967","version":1},"attestation_state":"computed","paper":{"title":"Robotic Search & Rescue via Online Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Lisa Lee","submitted_at":"2015-11-29T04:33:51Z","abstract_excerpt":"Reinforcement learning (RL) is a general and well-known method that a robot can use to learn an optimal control policy to solve a particular task. We would like to build a versatile robot that can learn multiple tasks, but using RL for each of them would be prohibitively expensive in terms of both time and wear-and-tear on the robot. To remedy this problem, we use the Policy Gradient Efficient Lifelong Learning Algorithm (PG-ELLA), an online multi-task RL algorithm that enables the robot to efficiently learn multiple consecutive tasks by sharing knowledge between these tasks to accelerate lear"},"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":"1511.08967","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-29T04:33:51Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"4bde8d65de0cbf88d561a1034e87df131886ea93793731ca9368312d28cc07d9","abstract_canon_sha256":"69f081e46d09019b363911ebbfc85ddf44b72408889e34a333bb28eaa18e8359"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:25:45.955581Z","signature_b64":"FInp8JERLp6drRMjFuMevk4OT49LeqdikCoanIQSiE3YpPFKL3EMORw+a2HF8JMOzMPfqKhKYd9WC6nwcmL3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4de761f6303978b902e2d97649eb3d0dc477fa9e276f484ed0ce26fbbe9ecb32","last_reissued_at":"2026-05-18T01:25:45.955141Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:25:45.955141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robotic Search & Rescue via Online Multi-task Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Lisa Lee","submitted_at":"2015-11-29T04:33:51Z","abstract_excerpt":"Reinforcement learning (RL) is a general and well-known method that a robot can use to learn an optimal control policy to solve a particular task. We would like to build a versatile robot that can learn multiple tasks, but using RL for each of them would be prohibitively expensive in terms of both time and wear-and-tear on the robot. To remedy this problem, we use the Policy Gradient Efficient Lifelong Learning Algorithm (PG-ELLA), an online multi-task RL algorithm that enables the robot to efficiently learn multiple consecutive tasks by sharing knowledge between these tasks to accelerate lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08967","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":"1511.08967","created_at":"2026-05-18T01:25:45.955200+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.08967v1","created_at":"2026-05-18T01:25:45.955200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08967","created_at":"2026-05-18T01:25:45.955200+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXTWD5RQHF4L","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXTWD5RQHF4LSAXC","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXTWD5RQ","created_at":"2026-05-18T12:29:27.538025+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/JXTWD5RQHF4LSAXC3F3ET2Z5BX","json":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX.json","graph_json":"https://pith.science/api/pith-number/JXTWD5RQHF4LSAXC3F3ET2Z5BX/graph.json","events_json":"https://pith.science/api/pith-number/JXTWD5RQHF4LSAXC3F3ET2Z5BX/events.json","paper":"https://pith.science/paper/JXTWD5RQ"},"agent_actions":{"view_html":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX","download_json":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX.json","view_paper":"https://pith.science/paper/JXTWD5RQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.08967&json=true","fetch_graph":"https://pith.science/api/pith-number/JXTWD5RQHF4LSAXC3F3ET2Z5BX/graph.json","fetch_events":"https://pith.science/api/pith-number/JXTWD5RQHF4LSAXC3F3ET2Z5BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX/action/storage_attestation","attest_author":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX/action/author_attestation","sign_citation":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX/action/citation_signature","submit_replication":"https://pith.science/pith/JXTWD5RQHF4LSAXC3F3ET2Z5BX/action/replication_record"}},"created_at":"2026-05-18T01:25:45.955200+00:00","updated_at":"2026-05-18T01:25:45.955200+00:00"}