{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:XSMH6XH2MKEBQZSOCPK74BWFZK","short_pith_number":"pith:XSMH6XH2","schema_version":"1.0","canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","source":{"kind":"arxiv","id":"1207.4114","version":1},"attestation_state":"computed","paper":{"title":"Metrics for Finite Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Norman Ferns, Prakash Panangaden","submitted_at":"2012-07-11T14:43:04Z","abstract_excerpt":"We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP."},"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":"1207.4114","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-07-11T14:43:04Z","cross_cats_sorted":[],"title_canon_sha256":"17151a3de3688cc2af74d4c27f7dccf5bfd3e6e57ccff4f0069db77630f1cccd","abstract_canon_sha256":"649583ad31fbafa578d07eccec532eb218105adc6301b1c34cff82b7b9c41d39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:47.950455Z","signature_b64":"30DFp4x68nllKCcVUjei7pcpg1VHkM+5UTwIpQcYYRB0izbB03GZUVTXZWj0CW/+Z+qCuO184ZyS2uz6xfMBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc987f5cfa628818664e13d5fe06c5cabd96d9f4efdd70ed6001ff81906f012b","last_reissued_at":"2026-05-18T03:50:47.949830Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:47.949830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Metrics for Finite Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Norman Ferns, Prakash Panangaden","submitted_at":"2012-07-11T14:43:04Z","abstract_excerpt":"We present metrics for measuring the similarity of states in a finite Markov decision process (MDP). The formulation of our metrics is based on the notion of bisimulation for MDPs, with an aim towards solving discounted infinite horizon reinforcement learning tasks. Such metrics can be used to aggregate states, as well as to better structure other value function approximators (e.g., memory-based or nearest-neighbor approximators). We provide bounds that relate our metric distances to the optimal values of states in the given MDP."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.4114","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":"1207.4114","created_at":"2026-05-18T03:50:47.949916+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.4114v1","created_at":"2026-05-18T03:50:47.949916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.4114","created_at":"2026-05-18T03:50:47.949916+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSMH6XH2MKEB","created_at":"2026-05-18T12:27:27.928770+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSMH6XH2MKEBQZSO","created_at":"2026-05-18T12:27:27.928770+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSMH6XH2","created_at":"2026-05-18T12:27:27.928770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK","json":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK.json","graph_json":"https://pith.science/api/pith-number/XSMH6XH2MKEBQZSOCPK74BWFZK/graph.json","events_json":"https://pith.science/api/pith-number/XSMH6XH2MKEBQZSOCPK74BWFZK/events.json","paper":"https://pith.science/paper/XSMH6XH2"},"agent_actions":{"view_html":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK","download_json":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK.json","view_paper":"https://pith.science/paper/XSMH6XH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.4114&json=true","fetch_graph":"https://pith.science/api/pith-number/XSMH6XH2MKEBQZSOCPK74BWFZK/graph.json","fetch_events":"https://pith.science/api/pith-number/XSMH6XH2MKEBQZSOCPK74BWFZK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/action/storage_attestation","attest_author":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/action/author_attestation","sign_citation":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/action/citation_signature","submit_replication":"https://pith.science/pith/XSMH6XH2MKEBQZSOCPK74BWFZK/action/replication_record"}},"created_at":"2026-05-18T03:50:47.949916+00:00","updated_at":"2026-05-18T03:50:47.949916+00:00"}