{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:NXLPKP4ZDNFM7TCAASBEH3WJXE","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":"273f3763f16b7685b4683343d152f7df687e91b11fe3caa23de69c6a132ea4f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-05-21T17:24:57Z","title_canon_sha256":"a99afce836eccf3ee902b4b7c31f7ff07afd02ef88307585c48330c9c336952b"},"schema_version":"1.0","source":{"id":"1505.05798","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1505.05798","created_at":"2026-05-18T02:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"1505.05798v1","created_at":"2026-05-18T02:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05798","created_at":"2026-05-18T02:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"NXLPKP4ZDNFM","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NXLPKP4ZDNFM7TCA","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NXLPKP4Z","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:ec1899c94e875d387cda4937279af36f9e02b70fd81ca453adcac9b7f8728068","target":"graph","created_at":"2026-05-18T02:03:53Z","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":"Lifelong reinforcement learning provides a promising framework for developing versatile agents that can accumulate knowledge over a lifetime of experience and rapidly learn new tasks by building upon prior knowledge. However, current lifelong learning methods exhibit non-vanishing regret as the amount of experience increases and include limitations that can lead to suboptimal or unsafe control policies. To address these issues, we develop a lifelong policy gradient learner that operates in an adversarial set- ting to learn multiple tasks online while enforcing safety constraints on the learned","authors_text":"Eric Eaton, Haitham Bou Ammar, Rasul Tutunov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-05-21T17:24:57Z","title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05798","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":"sha256:7167e1f1e7cafa904bff75c4f130f65c4fa8f8b5afc61281517e3f4ef591e221","target":"record","created_at":"2026-05-18T02:03:53Z","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":"273f3763f16b7685b4683343d152f7df687e91b11fe3caa23de69c6a132ea4f0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-05-21T17:24:57Z","title_canon_sha256":"a99afce836eccf3ee902b4b7c31f7ff07afd02ef88307585c48330c9c336952b"},"schema_version":"1.0","source":{"id":"1505.05798","kind":"arxiv","version":1}},"canonical_sha256":"6dd6f53f991b4acfcc40048243eec9b90cfc3ef21ffa2ed184d05166663157ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6dd6f53f991b4acfcc40048243eec9b90cfc3ef21ffa2ed184d05166663157ae","first_computed_at":"2026-05-18T02:03:53.446443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:03:53.446443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XHTyvo0Kj8p0lR2Nnf/QbJM5O3k40iEOA+xu8n68+XjiRPZNRH9PsMuK3/FGf3AA3QdoEYnZbyFyuWX7twZvAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:03:53.447139Z","signed_message":"canonical_sha256_bytes"},"source_id":"1505.05798","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7167e1f1e7cafa904bff75c4f130f65c4fa8f8b5afc61281517e3f4ef591e221","sha256:ec1899c94e875d387cda4937279af36f9e02b70fd81ca453adcac9b7f8728068"],"state_sha256":"52808cd70e6364ff1fbc3746fae78e27e6a668cae5d5d9f5acf75b3a56342127"}