{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5GJZ72FUCEVHSBTN2ATYLCYXIR","short_pith_number":"pith:5GJZ72FU","schema_version":"1.0","canonical_sha256":"e9939fe8b4112a79066dd027858b1744483e98791e1003e78c83e5f0217c6da6","source":{"kind":"arxiv","id":"2007.01498","version":2},"attestation_state":"computed","paper":{"title":"Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bo Wu, Peter Stone, Rishi Shah, Sudarshanan Bharadwaj, Ufuk Topcu, Yuqian Jiang","submitted_at":"2020-07-03T05:06:57Z","abstract_excerpt":"In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward shaping is a common approach for incorporating domain knowledge into reinforcement learning in order to speed up convergence to an optimal policy. However, to the best of our knowledge, the theoretical properties of reward shaping have thus far only been established in the discounted setting. This paper presents the first "},"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":"2007.01498","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-07-03T05:06:57Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"edfed9c8973094cad6544500f04c2126038ffcb564f1fe7e6f024b21f4226ac5","abstract_canon_sha256":"d7c87446ceddc3c40c7fe8f1f9356be24edf4e029c2aeb45f615c1ada8facbac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:33:03.650667Z","signature_b64":"N6DpTzZ4ZKB+2jYlfhzIPBFGVIMqQB5X++7fawZogja7aKVfOSBKmB7+3VqKNJVTybVOUYzoAdRAN+OXn/AECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9939fe8b4112a79066dd027858b1744483e98791e1003e78c83e5f0217c6da6","last_reissued_at":"2026-07-05T05:33:03.650164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:33:03.650164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Bo Wu, Peter Stone, Rishi Shah, Sudarshanan Bharadwaj, Ufuk Topcu, Yuqian Jiang","submitted_at":"2020-07-03T05:06:57Z","abstract_excerpt":"In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward shaping is a common approach for incorporating domain knowledge into reinforcement learning in order to speed up convergence to an optimal policy. However, to the best of our knowledge, the theoretical properties of reward shaping have thus far only been established in the discounted setting. This paper presents the first "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.01498","kind":"arxiv","version":2},"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/2007.01498/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":"2007.01498","created_at":"2026-07-05T05:33:03.650222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.01498v2","created_at":"2026-07-05T05:33:03.650222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.01498","created_at":"2026-07-05T05:33:03.650222+00:00"},{"alias_kind":"pith_short_12","alias_value":"5GJZ72FUCEVH","created_at":"2026-07-05T05:33:03.650222+00:00"},{"alias_kind":"pith_short_16","alias_value":"5GJZ72FUCEVHSBTN","created_at":"2026-07-05T05:33:03.650222+00:00"},{"alias_kind":"pith_short_8","alias_value":"5GJZ72FU","created_at":"2026-07-05T05:33:03.650222+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14440","citing_title":"On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR","json":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR.json","graph_json":"https://pith.science/api/pith-number/5GJZ72FUCEVHSBTN2ATYLCYXIR/graph.json","events_json":"https://pith.science/api/pith-number/5GJZ72FUCEVHSBTN2ATYLCYXIR/events.json","paper":"https://pith.science/paper/5GJZ72FU"},"agent_actions":{"view_html":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR","download_json":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR.json","view_paper":"https://pith.science/paper/5GJZ72FU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.01498&json=true","fetch_graph":"https://pith.science/api/pith-number/5GJZ72FUCEVHSBTN2ATYLCYXIR/graph.json","fetch_events":"https://pith.science/api/pith-number/5GJZ72FUCEVHSBTN2ATYLCYXIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR/action/storage_attestation","attest_author":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR/action/author_attestation","sign_citation":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR/action/citation_signature","submit_replication":"https://pith.science/pith/5GJZ72FUCEVHSBTN2ATYLCYXIR/action/replication_record"}},"created_at":"2026-07-05T05:33:03.650222+00:00","updated_at":"2026-07-05T05:33:03.650222+00:00"}