{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZK2JORBQ53BLLTV3N5PWKSE3PO","short_pith_number":"pith:ZK2JORBQ","schema_version":"1.0","canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","source":{"kind":"arxiv","id":"2607.17560","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning: From Algorithms To Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zihan Ding","submitted_at":"2026-07-20T05:09:36Z","abstract_excerpt":"Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models.\n  The first part focuses on multi-agent RL in games. It examin"},"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":"2607.17560","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T05:09:36Z","cross_cats_sorted":[],"title_canon_sha256":"26c562a60c5dcf45510358ae5c0c3e9e8a348d78d9f8cc4b2fe081cf3cb2c4f3","abstract_canon_sha256":"6bb32ca8d04908a468c11be360b69e27c51512be426e6e679c569a94a9d83795"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:52.296106Z","signature_b64":"WDogBNhXGRQpx4Nft5hvBzubSEGq0NxsiK7dgEe3MzRasmnWw0QN9/sAwkr1bT/JL4HwobbkF6MPubuT31nkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cab4974430eec2b5cebb6f5f65489b7baf6be49f6d201157fe5fc7aaf42e9818","last_reissued_at":"2026-07-21T01:21:52.295212Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:52.295212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning: From Algorithms To Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Zihan Ding","submitted_at":"2026-07-20T05:09:36Z","abstract_excerpt":"Reinforcement learning (RL) provides a framework for sequential decision making under explicit objectives. In its classical form, RL studies how an agent should act to maximise long-term reward in a dynamic environment. In richer settings, the problem extends beyond a single agent and fixed environment: intelligent behavior may require strategic interaction, adaptation to uncertainty, and reasoning over high-dimensional worlds. This thesis studies RL from two perspectives: algorithms in games and RL in the era of foundation models.\n  The first part focuses on multi-agent RL in games. It examin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17560","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/2607.17560/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":"2607.17560","created_at":"2026-07-21T01:21:52.295696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17560v1","created_at":"2026-07-21T01:21:52.295696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17560","created_at":"2026-07-21T01:21:52.295696+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZK2JORBQ53BL","created_at":"2026-07-21T01:21:52.295696+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZK2JORBQ53BLLTV3","created_at":"2026-07-21T01:21:52.295696+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZK2JORBQ","created_at":"2026-07-21T01:21:52.295696+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/ZK2JORBQ53BLLTV3N5PWKSE3PO","json":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO.json","graph_json":"https://pith.science/api/pith-number/ZK2JORBQ53BLLTV3N5PWKSE3PO/graph.json","events_json":"https://pith.science/api/pith-number/ZK2JORBQ53BLLTV3N5PWKSE3PO/events.json","paper":"https://pith.science/paper/ZK2JORBQ"},"agent_actions":{"view_html":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO","download_json":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO.json","view_paper":"https://pith.science/paper/ZK2JORBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17560&json=true","fetch_graph":"https://pith.science/api/pith-number/ZK2JORBQ53BLLTV3N5PWKSE3PO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZK2JORBQ53BLLTV3N5PWKSE3PO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/action/storage_attestation","attest_author":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/action/author_attestation","sign_citation":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/action/citation_signature","submit_replication":"https://pith.science/pith/ZK2JORBQ53BLLTV3N5PWKSE3PO/action/replication_record"}},"created_at":"2026-07-21T01:21:52.295696+00:00","updated_at":"2026-07-21T01:21:52.295696+00:00"}