{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:NXLPKP4ZDNFM7TCAASBEH3WJXE","short_pith_number":"pith:NXLPKP4Z","schema_version":"1.0","canonical_sha256":"6dd6f53f991b4acfcc40048243eec9b90cfc3ef21ffa2ed184d05166663157ae","source":{"kind":"arxiv","id":"1505.05798","version":1},"attestation_state":"computed","paper":{"title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Eaton, Haitham Bou Ammar, Rasul Tutunov","submitted_at":"2015-05-21T17:24:57Z","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"},"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":"1505.05798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-05-21T17:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"a99afce836eccf3ee902b4b7c31f7ff07afd02ef88307585c48330c9c336952b","abstract_canon_sha256":"273f3763f16b7685b4683343d152f7df687e91b11fe3caa23de69c6a132ea4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:03:53.447139Z","signature_b64":"XHTyvo0Kj8p0lR2Nnf/QbJM5O3k40iEOA+xu8n68+XjiRPZNRH9PsMuK3/FGf3AA3QdoEYnZbyFyuWX7twZvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dd6f53f991b4acfcc40048243eec9b90cfc3ef21ffa2ed184d05166663157ae","last_reissued_at":"2026-05-18T02:03:53.446443Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:03:53.446443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe Policy Search for Lifelong Reinforcement Learning with Sublinear Regret","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Eaton, Haitham Bou Ammar, Rasul Tutunov","submitted_at":"2015-05-21T17:24:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05798","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":"1505.05798","created_at":"2026-05-18T02:03:53.446560+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.05798v1","created_at":"2026-05-18T02:03:53.446560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05798","created_at":"2026-05-18T02:03:53.446560+00:00"},{"alias_kind":"pith_short_12","alias_value":"NXLPKP4ZDNFM","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"NXLPKP4ZDNFM7TCA","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"NXLPKP4Z","created_at":"2026-05-18T12:29:34.919912+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/NXLPKP4ZDNFM7TCAASBEH3WJXE","json":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE.json","graph_json":"https://pith.science/api/pith-number/NXLPKP4ZDNFM7TCAASBEH3WJXE/graph.json","events_json":"https://pith.science/api/pith-number/NXLPKP4ZDNFM7TCAASBEH3WJXE/events.json","paper":"https://pith.science/paper/NXLPKP4Z"},"agent_actions":{"view_html":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE","download_json":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE.json","view_paper":"https://pith.science/paper/NXLPKP4Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.05798&json=true","fetch_graph":"https://pith.science/api/pith-number/NXLPKP4ZDNFM7TCAASBEH3WJXE/graph.json","fetch_events":"https://pith.science/api/pith-number/NXLPKP4ZDNFM7TCAASBEH3WJXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE/action/storage_attestation","attest_author":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE/action/author_attestation","sign_citation":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE/action/citation_signature","submit_replication":"https://pith.science/pith/NXLPKP4ZDNFM7TCAASBEH3WJXE/action/replication_record"}},"created_at":"2026-05-18T02:03:53.446560+00:00","updated_at":"2026-05-18T02:03:53.446560+00:00"}