{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7HXAOQNFXFTO6OJXNFO775ELYF","short_pith_number":"pith:7HXAOQNF","schema_version":"1.0","canonical_sha256":"f9ee0741a5b966ef3937695dfff48bc162c05e60ccaf3060830a9c05ef9c57db","source":{"kind":"arxiv","id":"2410.10578","version":11},"attestation_state":"computed","paper":{"title":"Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi-Guhn Lee, Juan Sebastian Rojas","submitted_at":"2024-10-14T14:52:23Z","abstract_excerpt":"Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with the majority of RL-based efforts having been allocated to discounted MDPs. In this work, we study a unique structural property of average-reward MDPs and utilize it to introduce Reward-Extended Differential (or RED) reinforcement learning: a novel RL framework that can be used to effectively and efficiently solve various learning objectives, or subtasks, simu"},"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":"2410.10578","kind":"arxiv","version":11},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-14T14:52:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21e08cfe747b862cf8a3a4b6efd15145b658db7b792c69c3c54edf9e48cad9de","abstract_canon_sha256":"843d4a8ee5b3d23bc415597cca522849a2a4b9f9450082a92ab2b6c73fa9113e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:44.299154Z","signature_b64":"TAcb89z7p9GJ6PcG/Ie8ua9ah0YUlFj9accLrjkqceBrZ6pgIXi4YPiB7/V1XzQKpNOUVVxP9o9ceKy9P0k2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ee0741a5b966ef3937695dfff48bc162c05e60ccaf3060830a9c05ef9c57db","last_reissued_at":"2026-07-05T12:00:44.298656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:44.298656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Burning RED: Unlocking Subtask-Driven Reinforcement Learning and Risk-Awareness in Average-Reward Markov Decision Processes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi-Guhn Lee, Juan Sebastian Rojas","submitted_at":"2024-10-14T14:52:23Z","abstract_excerpt":"Average-reward Markov decision processes (MDPs) provide a foundational framework for sequential decision-making under uncertainty. However, average-reward MDPs have remained largely unexplored in reinforcement learning (RL) settings, with the majority of RL-based efforts having been allocated to discounted MDPs. In this work, we study a unique structural property of average-reward MDPs and utilize it to introduce Reward-Extended Differential (or RED) reinforcement learning: a novel RL framework that can be used to effectively and efficiently solve various learning objectives, or subtasks, simu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10578","kind":"arxiv","version":11},"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/2410.10578/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":"2410.10578","created_at":"2026-07-05T12:00:44.298712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10578v11","created_at":"2026-07-05T12:00:44.298712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10578","created_at":"2026-07-05T12:00:44.298712+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HXAOQNFXFTO","created_at":"2026-07-05T12:00:44.298712+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HXAOQNFXFTO6OJX","created_at":"2026-07-05T12:00:44.298712+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HXAOQNF","created_at":"2026-07-05T12:00:44.298712+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/7HXAOQNFXFTO6OJXNFO775ELYF","json":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF.json","graph_json":"https://pith.science/api/pith-number/7HXAOQNFXFTO6OJXNFO775ELYF/graph.json","events_json":"https://pith.science/api/pith-number/7HXAOQNFXFTO6OJXNFO775ELYF/events.json","paper":"https://pith.science/paper/7HXAOQNF"},"agent_actions":{"view_html":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF","download_json":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF.json","view_paper":"https://pith.science/paper/7HXAOQNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10578&json=true","fetch_graph":"https://pith.science/api/pith-number/7HXAOQNFXFTO6OJXNFO775ELYF/graph.json","fetch_events":"https://pith.science/api/pith-number/7HXAOQNFXFTO6OJXNFO775ELYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF/action/storage_attestation","attest_author":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF/action/author_attestation","sign_citation":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF/action/citation_signature","submit_replication":"https://pith.science/pith/7HXAOQNFXFTO6OJXNFO775ELYF/action/replication_record"}},"created_at":"2026-07-05T12:00:44.298712+00:00","updated_at":"2026-07-05T12:00:44.298712+00:00"}