{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZXEALUM5VXS564J5T6YD3LSMCM","short_pith_number":"pith:ZXEALUM5","schema_version":"1.0","canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","source":{"kind":"arxiv","id":"2001.09293","version":1},"attestation_state":"computed","paper":{"title":"Learning Non-Markovian Reward Models in MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gavin Rens, Jean-Fran\\c{c}ois Raskin","submitted_at":"2020-01-25T10:51:42Z","abstract_excerpt":"There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks. In other words, the reward that the agent receives is non-Markovian. One natural and quite general way to represent history-dependent rewards is via a Mealy machine; a finite state automaton that produces output sequences (rewards in our case) from input sequences (state/action observations in our case). In our formal setting, we consider a Markov decision process (MDP) that models the dynamic of the environment in which the agent evolves and a Mealy machine synchronised wit"},"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":"2001.09293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"1d1ea8f2f2ccc7c9afbb783fb59fc833ca8f4f9c47b59b505dd14ac8a48e1557","abstract_canon_sha256":"f7b70948ba95f51cc0528be24c6830795eb1c78f36cd370f4f13e26df49d9421"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:57.961596Z","signature_b64":"qzTkzIvbdc0Ck3if+XnBDiXGXPL6LrKoRxzBiAg4lGxy0HULSQeXGXqXsYvBTfEH8vyHlcA2rphpJUPohv/cDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","last_reissued_at":"2026-07-05T00:35:57.961175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:57.961175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Non-Markovian Reward Models in MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gavin Rens, Jean-Fran\\c{c}ois Raskin","submitted_at":"2020-01-25T10:51:42Z","abstract_excerpt":"There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks. In other words, the reward that the agent receives is non-Markovian. One natural and quite general way to represent history-dependent rewards is via a Mealy machine; a finite state automaton that produces output sequences (rewards in our case) from input sequences (state/action observations in our case). In our formal setting, we consider a Markov decision process (MDP) that models the dynamic of the environment in which the agent evolves and a Mealy machine synchronised wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09293","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.09293/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.09293","created_at":"2026-07-05T00:35:57.961236+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.09293v1","created_at":"2026-07-05T00:35:57.961236+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09293","created_at":"2026-07-05T00:35:57.961236+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXEALUM5VXS5","created_at":"2026-07-05T00:35:57.961236+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXEALUM5VXS564J5","created_at":"2026-07-05T00:35:57.961236+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXEALUM5","created_at":"2026-07-05T00:35:57.961236+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.04282","citing_title":"Synthetic POMDPs to Challenge Memory-Augmented RL: Memory Demand Structure Modeling","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM","json":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM.json","graph_json":"https://pith.science/api/pith-number/ZXEALUM5VXS564J5T6YD3LSMCM/graph.json","events_json":"https://pith.science/api/pith-number/ZXEALUM5VXS564J5T6YD3LSMCM/events.json","paper":"https://pith.science/paper/ZXEALUM5"},"agent_actions":{"view_html":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM","download_json":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM.json","view_paper":"https://pith.science/paper/ZXEALUM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.09293&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXEALUM5VXS564J5T6YD3LSMCM/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXEALUM5VXS564J5T6YD3LSMCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/action/storage_attestation","attest_author":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/action/author_attestation","sign_citation":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/action/citation_signature","submit_replication":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/action/replication_record"}},"created_at":"2026-07-05T00:35:57.961236+00:00","updated_at":"2026-07-05T00:35:57.961236+00:00"}