{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:GPJ33PSCZXTTZQXZP2VGRRUP2B","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":"defa227286ee1ad7fa7b4affd1298336c54fb80cc3315d9555a8207247de9984","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-11-15T19:40:58Z","title_canon_sha256":"6949de96f7aff5471abb175909df9d8bec29e98ee06f62210553e59ef723eed8"},"schema_version":"1.0","source":{"id":"1311.3959","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.3959","created_at":"2026-05-18T01:15:59Z"},{"alias_kind":"arxiv_version","alias_value":"1311.3959v4","created_at":"2026-05-18T01:15:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.3959","created_at":"2026-05-18T01:15:59Z"},{"alias_kind":"pith_short_12","alias_value":"GPJ33PSCZXTT","created_at":"2026-05-18T12:27:45Z"},{"alias_kind":"pith_short_16","alias_value":"GPJ33PSCZXTTZQXZ","created_at":"2026-05-18T12:27:45Z"},{"alias_kind":"pith_short_8","alias_value":"GPJ33PSC","created_at":"2026-05-18T12:27:45Z"}],"graph_snapshots":[{"event_id":"sha256:111d32e9e69afa5aa4e6e2fc0d172cabce133e64974304f90f8cb0ab31c4fc1e","target":"graph","created_at":"2026-05-18T01:15:59Z","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":"We present algorithms to effectively represent a set of Markov decision processes (MDPs), whose optimal policies have already been learned, by a smaller source subset for lifelong, policy-reuse-based transfer learning in reinforcement learning. This is necessary when the number of previous tasks is large and the cost of measuring similarity counteracts the benefit of transfer. The source subset forms an `$\\epsilon$-net' over the original set of MDPs, in the sense that for each previous MDP $M_p$, there is a source $M^s$ whose optimal policy has $<\\epsilon$ regret in $M_p$. Our contributions ar","authors_text":"Benjamin Rosman, Majd Hawasly, M. M. Hassan Mahmud, Subramanian Ramamoorthy","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-11-15T19:40:58Z","title":"Clustering Markov Decision Processes For Continual Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.3959","kind":"arxiv","version":4},"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":"sha256:17cfa0c4bff1def066b38b2864af099ee203e328331c59082a50a0ef09fe00bc","target":"record","created_at":"2026-05-18T01:15:59Z","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":"defa227286ee1ad7fa7b4affd1298336c54fb80cc3315d9555a8207247de9984","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2013-11-15T19:40:58Z","title_canon_sha256":"6949de96f7aff5471abb175909df9d8bec29e98ee06f62210553e59ef723eed8"},"schema_version":"1.0","source":{"id":"1311.3959","kind":"arxiv","version":4}},"canonical_sha256":"33d3bdbe42cde73cc2f97eaa68c68fd07937790777f5c3719df3ede7b8876737","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33d3bdbe42cde73cc2f97eaa68c68fd07937790777f5c3719df3ede7b8876737","first_computed_at":"2026-05-18T01:15:59.273833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:15:59.273833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9uSxDNHQhaEoM6aareQYMQwiE6LaOefBhtxGFWKroht0sG3c/hAEQd1hCAoCf21woSNnUC72c8ojFWKoKsbvDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:15:59.274813Z","signed_message":"canonical_sha256_bytes"},"source_id":"1311.3959","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17cfa0c4bff1def066b38b2864af099ee203e328331c59082a50a0ef09fe00bc","sha256:111d32e9e69afa5aa4e6e2fc0d172cabce133e64974304f90f8cb0ab31c4fc1e"],"state_sha256":"85b7411c6312b94baace3a64786bc4d86269db075c84caffab7de3cbfbae7293"}