{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IQEBSB5WQR6SYMF5MRVG2Q65GA","short_pith_number":"pith:IQEBSB5W","schema_version":"1.0","canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","source":{"kind":"arxiv","id":"1609.01995","version":4},"attestation_state":"computed","paper":{"title":"Unifying task specification in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Martha White","submitted_at":"2016-09-07T14:27:56Z","abstract_excerpt":"Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we de"},"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":"1609.01995","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-07T14:27:56Z","cross_cats_sorted":[],"title_canon_sha256":"842f10194d76b1372e69a94970772c78937a4626f60c6d5ea6720ded98559ff3","abstract_canon_sha256":"53c4db219ee8865bba32256cd809588d5c933ffd634ed2f50f6e28f616db65be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:24.744091Z","signature_b64":"t7cOOLSrOSXN55+3EvN/V6GkVMLXNMC1kc4w5oTIL+BSoGRWj3y7iICk9pDleZxDBnbWnm4jmjaAGA6sX30xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44081907b6847d2c30bd646a6d43dd303ff168abff5bf05b2ecf4cafd4af8138","last_reissued_at":"2026-07-05T03:15:24.743734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:24.743734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unifying task specification in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Martha White","submitted_at":"2016-09-07T14:27:56Z","abstract_excerpt":"Reinforcement learning tasks are typically specified as Markov decision processes. This formalism has been highly successful, though specifications often couple the dynamics of the environment and the learning objective. This lack of modularity can complicate generalization of the task specification, as well as obfuscate connections between different task settings, such as episodic and continuing. In this work, we introduce the RL task formalism, that provides a unification through simple constructs including a generalization to transition-based discounting. Through a series of examples, we de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.01995","kind":"arxiv","version":4},"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/1609.01995/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":"1609.01995","created_at":"2026-07-05T03:15:24.743790+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.01995v4","created_at":"2026-07-05T03:15:24.743790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.01995","created_at":"2026-07-05T03:15:24.743790+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQEBSB5WQR6S","created_at":"2026-07-05T03:15:24.743790+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQEBSB5WQR6SYMF5","created_at":"2026-07-05T03:15:24.743790+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQEBSB5W","created_at":"2026-07-05T03:15:24.743790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04368","citing_title":"Extending Differential Temporal Difference Methods for Episodic Problems","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA","json":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA.json","graph_json":"https://pith.science/api/pith-number/IQEBSB5WQR6SYMF5MRVG2Q65GA/graph.json","events_json":"https://pith.science/api/pith-number/IQEBSB5WQR6SYMF5MRVG2Q65GA/events.json","paper":"https://pith.science/paper/IQEBSB5W"},"agent_actions":{"view_html":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA","download_json":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA.json","view_paper":"https://pith.science/paper/IQEBSB5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.01995&json=true","fetch_graph":"https://pith.science/api/pith-number/IQEBSB5WQR6SYMF5MRVG2Q65GA/graph.json","fetch_events":"https://pith.science/api/pith-number/IQEBSB5WQR6SYMF5MRVG2Q65GA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/action/storage_attestation","attest_author":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/action/author_attestation","sign_citation":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/action/citation_signature","submit_replication":"https://pith.science/pith/IQEBSB5WQR6SYMF5MRVG2Q65GA/action/replication_record"}},"created_at":"2026-07-05T03:15:24.743790+00:00","updated_at":"2026-07-05T03:15:24.743790+00:00"}