{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:QTTXG7EXDO4B3XJDHAPSFPSOSS","short_pith_number":"pith:QTTXG7EX","canonical_record":{"source":{"id":"1506.03379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f9175720b713d871ad07f391fe055c2242501fd50c776570d13a2652c66039a","abstract_canon_sha256":"b3654843082d11d2306e1bd8a28f5d0d3d21a8f4a7f936c69ee520f66399ddd4"},"schema_version":"1.0"},"canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","source":{"kind":"arxiv","id":"1506.03379","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03379","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03379v2","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03379","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"pith_short_12","alias_value":"QTTXG7EXDO4B","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"QTTXG7EXDO4B3XJD","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"QTTXG7EX","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:QTTXG7EXDO4B3XJDHAPSFPSOSS","target":"record","payload":{"canonical_record":{"source":{"id":"1506.03379","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f9175720b713d871ad07f391fe055c2242501fd50c776570d13a2652c66039a","abstract_canon_sha256":"b3654843082d11d2306e1bd8a28f5d0d3d21a8f4a7f936c69ee520f66399ddd4"},"schema_version":"1.0"},"canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:29.174878Z","signature_b64":"asp7CHjPf4oW8G4m3CFXzoUb+K382kKiZEMk9PcIBg8EnWCxc2daFvk4cYYethcFXo2hddQyvAACGrkgnt3+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","last_reissued_at":"2026-05-18T01:32:29.174368Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:29.174368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1506.03379","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NMuUtLbV8BrB+cHAbGTUyEacCQ3L0eEu/4tOjXofQSz8WjTNajV6ws3z5q5VGCc3fZc1/SU0RW+afTEWuydIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:56:17.860466Z"},"content_sha256":"706b748acb980e68ff62a72f823f0f27e74f340e73d0c0560a84d4656a147357","schema_version":"1.0","event_id":"sha256:706b748acb980e68ff62a72f823f0f27e74f340e73d0c0560a84d4656a147357"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:QTTXG7EXDO4B3XJDHAPSFPSOSS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Emma Brunskill, Lihong Li","submitted_at":"2015-06-10T16:23:29Z","abstract_excerpt":"Transferring knowledge across a sequence of related tasks is an important challenge in reinforcement learning (RL). Despite much encouraging empirical evidence, there has been little theoretical analysis. In this paper, we study a class of lifelong RL problems: the agent solves a sequence of tasks modeled as finite Markov decision processes (MDPs), each of which is from a finite set of MDPs with the same state/action sets and different transition/reward functions. Motivated by the need for cross-task exploration in lifelong learning, we formulate a novel online coupon-collector problem and giv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03379","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXmwzWWQYTSpW/VySy+scuyafmbsz/iswUHMroEc1pau/MA3iPV2AzP4QXcl55bTTW2mnW5aDj8vZyhNPfFZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:56:17.861089Z"},"content_sha256":"97491d9952223a820740261cc061aa2476338f7c09293b89b969fab6e033fb1a","schema_version":"1.0","event_id":"sha256:97491d9952223a820740261cc061aa2476338f7c09293b89b969fab6e033fb1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/bundle.json","state_url":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T02:56:17Z","links":{"resolver":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS","bundle":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/bundle.json","state":"https://pith.science/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QTTXG7EXDO4B3XJDHAPSFPSOSS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:QTTXG7EXDO4B3XJDHAPSFPSOSS","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":"b3654843082d11d2306e1bd8a28f5d0d3d21a8f4a7f936c69ee520f66399ddd4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","title_canon_sha256":"2f9175720b713d871ad07f391fe055c2242501fd50c776570d13a2652c66039a"},"schema_version":"1.0","source":{"id":"1506.03379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1506.03379","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"arxiv_version","alias_value":"1506.03379v2","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03379","created_at":"2026-05-18T01:32:29Z"},{"alias_kind":"pith_short_12","alias_value":"QTTXG7EXDO4B","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"QTTXG7EXDO4B3XJD","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"QTTXG7EX","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:97491d9952223a820740261cc061aa2476338f7c09293b89b969fab6e033fb1a","target":"graph","created_at":"2026-05-18T01:32:29Z","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":"Transferring knowledge across a sequence of related tasks is an important challenge in reinforcement learning (RL). Despite much encouraging empirical evidence, there has been little theoretical analysis. In this paper, we study a class of lifelong RL problems: the agent solves a sequence of tasks modeled as finite Markov decision processes (MDPs), each of which is from a finite set of MDPs with the same state/action sets and different transition/reward functions. Motivated by the need for cross-task exploration in lifelong learning, we formulate a novel online coupon-collector problem and giv","authors_text":"Emma Brunskill, Lihong Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","title":"The Online Coupon-Collector Problem and Its Application to Lifelong Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03379","kind":"arxiv","version":2},"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":"sha256:706b748acb980e68ff62a72f823f0f27e74f340e73d0c0560a84d4656a147357","target":"record","created_at":"2026-05-18T01:32:29Z","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":"b3654843082d11d2306e1bd8a28f5d0d3d21a8f4a7f936c69ee520f66399ddd4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-10T16:23:29Z","title_canon_sha256":"2f9175720b713d871ad07f391fe055c2242501fd50c776570d13a2652c66039a"},"schema_version":"1.0","source":{"id":"1506.03379","kind":"arxiv","version":2}},"canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84e7737c971bb81ddd23381f22be4e948c3fee4df9efd581b24cf8dfcf7e57a6","first_computed_at":"2026-05-18T01:32:29.174368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:29.174368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"asp7CHjPf4oW8G4m3CFXzoUb+K382kKiZEMk9PcIBg8EnWCxc2daFvk4cYYethcFXo2hddQyvAACGrkgnt3+CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:29.174878Z","signed_message":"canonical_sha256_bytes"},"source_id":"1506.03379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:706b748acb980e68ff62a72f823f0f27e74f340e73d0c0560a84d4656a147357","sha256:97491d9952223a820740261cc061aa2476338f7c09293b89b969fab6e033fb1a"],"state_sha256":"7530f1fb0928b2c46f5f21c7aa4aa61e29f00eb6d55ea85c070b4ff20c8f2a3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J69tZAQAsCyoBNZnlVg58EPF0qW2ndrpkTfyYaWW/P8qcpDa+vNCv7KOReil/0YXnDuHmUoEzbP8vAJFW36MCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T02:56:17.864907Z","bundle_sha256":"1baae106506cb752e278935a9de4fa761089d010588805e317ba0db4815aded9"}}