{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:J5PXZ3DC5N2HFGFW4OH2RQN6VC","short_pith_number":"pith:J5PXZ3DC","schema_version":"1.0","canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","source":{"kind":"arxiv","id":"1902.02893","version":1},"attestation_state":"computed","paper":{"title":"Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Silviu Pitis","submitted_at":"2019-02-08T00:30:53Z","abstract_excerpt":"Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\\gamma < 1$, or in episodic settings, with $\\gamma = 1$. While this has proven effective for specific tasks with well-defined objectives (e.g., games), it has never been established that fixed discounting is suitable for general purpose use (e.g., as a model of human preferences). This paper characterizes rationality in sequential decision making using a set of seven axioms and arrives at a form of di"},"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":"1902.02893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-08T00:30:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"77c8cfe082a15229bb5e5be7b21662e9b5c94cbef2681071391d51ce9cb00675","abstract_canon_sha256":"bc11034241e102a20eb5614e023ead8a729b97169259b803d13cab8e5e224210"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:28.935573Z","signature_b64":"y8XVHqwG7OMOoSL23IR3NbJ6fNiuTWI/fIW3x9hBt0Tz638dnVRDBr1D8fOqhUt/zeToN2YK3NR35dNs+12+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f5f7cec62eb747298b6e38fa8c1bea8a06c6c95311832ff575924033603c17d","last_reissued_at":"2026-05-17T23:54:28.935137Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:28.935137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Silviu Pitis","submitted_at":"2019-02-08T00:30:53Z","abstract_excerpt":"Reinforcement learning (RL) agents have traditionally been tasked with maximizing the value function of a Markov decision process (MDP), either in continuous settings, with fixed discount factor $\\gamma < 1$, or in episodic settings, with $\\gamma = 1$. While this has proven effective for specific tasks with well-defined objectives (e.g., games), it has never been established that fixed discounting is suitable for general purpose use (e.g., as a model of human preferences). This paper characterizes rationality in sequential decision making using a set of seven axioms and arrives at a form of di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.02893","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":"1902.02893","created_at":"2026-05-17T23:54:28.935197+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.02893v1","created_at":"2026-05-17T23:54:28.935197+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.02893","created_at":"2026-05-17T23:54:28.935197+00:00"},{"alias_kind":"pith_short_12","alias_value":"J5PXZ3DC5N2H","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"J5PXZ3DC5N2HFGFW","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"J5PXZ3DC","created_at":"2026-05-18T12:33:18.533446+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/J5PXZ3DC5N2HFGFW4OH2RQN6VC","json":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC.json","graph_json":"https://pith.science/api/pith-number/J5PXZ3DC5N2HFGFW4OH2RQN6VC/graph.json","events_json":"https://pith.science/api/pith-number/J5PXZ3DC5N2HFGFW4OH2RQN6VC/events.json","paper":"https://pith.science/paper/J5PXZ3DC"},"agent_actions":{"view_html":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC","download_json":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC.json","view_paper":"https://pith.science/paper/J5PXZ3DC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.02893&json=true","fetch_graph":"https://pith.science/api/pith-number/J5PXZ3DC5N2HFGFW4OH2RQN6VC/graph.json","fetch_events":"https://pith.science/api/pith-number/J5PXZ3DC5N2HFGFW4OH2RQN6VC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/action/storage_attestation","attest_author":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/action/author_attestation","sign_citation":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/action/citation_signature","submit_replication":"https://pith.science/pith/J5PXZ3DC5N2HFGFW4OH2RQN6VC/action/replication_record"}},"created_at":"2026-05-17T23:54:28.935197+00:00","updated_at":"2026-05-17T23:54:28.935197+00:00"}