{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:JXTWD5RQHF4LSAXC3F3ET2Z5BX","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":"69f081e46d09019b363911ebbfc85ddf44b72408889e34a333bb28eaa18e8359","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-29T04:33:51Z","title_canon_sha256":"4bde8d65de0cbf88d561a1034e87df131886ea93793731ca9368312d28cc07d9"},"schema_version":"1.0","source":{"id":"1511.08967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08967","created_at":"2026-05-18T01:25:45Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08967v1","created_at":"2026-05-18T01:25:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08967","created_at":"2026-05-18T01:25:45Z"},{"alias_kind":"pith_short_12","alias_value":"JXTWD5RQHF4L","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JXTWD5RQHF4LSAXC","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JXTWD5RQ","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:3054f3ba56041dfb1463f6c967c5f4be3fa7b7a807fce8db92c3b566d2687de0","target":"graph","created_at":"2026-05-18T01:25:45Z","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":"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","authors_text":"Lisa Lee","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-29T04:33:51Z","title":"Robotic Search & Rescue via Online Multi-task Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08967","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":"sha256:9cba20dcacf35343da45f1f9ea0cc30783e8c6600ef59a283b4b493821f56db5","target":"record","created_at":"2026-05-18T01:25:45Z","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":"69f081e46d09019b363911ebbfc85ddf44b72408889e34a333bb28eaa18e8359","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-11-29T04:33:51Z","title_canon_sha256":"4bde8d65de0cbf88d561a1034e87df131886ea93793731ca9368312d28cc07d9"},"schema_version":"1.0","source":{"id":"1511.08967","kind":"arxiv","version":1}},"canonical_sha256":"4de761f6303978b902e2d97649eb3d0dc477fa9e276f484ed0ce26fbbe9ecb32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4de761f6303978b902e2d97649eb3d0dc477fa9e276f484ed0ce26fbbe9ecb32","first_computed_at":"2026-05-18T01:25:45.955141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:25:45.955141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FInp8JERLp6drRMjFuMevk4OT49LeqdikCoanIQSiE3YpPFKL3EMORw+a2HF8JMOzMPfqKhKYd9WC6nwcmL3Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:25:45.955581Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.08967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cba20dcacf35343da45f1f9ea0cc30783e8c6600ef59a283b4b493821f56db5","sha256:3054f3ba56041dfb1463f6c967c5f4be3fa7b7a807fce8db92c3b566d2687de0"],"state_sha256":"c6e4ba7f1632c3c56a5c1ff1f64c189f556afad95505d937d3a20236fdbb42a5"}