{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GHUK42ARTMTROFTSY2H6PT4WZN","short_pith_number":"pith:GHUK42AR","schema_version":"1.0","canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","source":{"kind":"arxiv","id":"2505.06319","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Lifeng Zhou, Zijian An","submitted_at":"2025-05-08T21:12:34Z","abstract_excerpt":"Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency "},"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":"2505.06319","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T21:12:34Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"012489dc205a0d8dda91db492a986b72afc7170b03be639520d8704251974e3c","abstract_canon_sha256":"8c3610cdd1bab1ada5a2633bb4064e57cba67826a62e78b3049f2c4db6b81906"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:07.351249Z","signature_b64":"4P2Oa90TYJDQgUAEvgHkWk1afH58gTDa0S/GFw9yo0I/QVbqx+h1XaYy9Vrrxs/jgu3bx40TlZ2Z9C8+LZkiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e8ae68119b27171672c68fe7cf96cb6409c994415cf1437b93ff5b8a68e845","last_reissued_at":"2026-07-05T11:01:07.350822Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:07.350822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Game-Theoretic Resource Allocation on Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Lifeng Zhou, Zijian An","submitted_at":"2025-05-08T21:12:34Z","abstract_excerpt":"Game-theoretic resource allocation on graphs (GRAG) involves two players competing over multiple steps to control nodes of interest on a graph, a problem modeled as a multi-step Colonel Blotto Game (MCBG). Finding optimal strategies is challenging due to the dynamic action space and structural constraints imposed by the graph. To address this, we formulate the MCBG as a Markov Decision Process (MDP) and apply Reinforcement Learning (RL) methods, specifically Deep Q-Network (DQN) and Proximal Policy Optimization (PPO). To enforce graph constraints, we introduce an action-displacement adjacency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06319","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/2505.06319/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":"2505.06319","created_at":"2026-07-05T11:01:07.350890+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06319v1","created_at":"2026-07-05T11:01:07.350890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06319","created_at":"2026-07-05T11:01:07.350890+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHUK42ARTMTR","created_at":"2026-07-05T11:01:07.350890+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHUK42ARTMTROFTS","created_at":"2026-07-05T11:01:07.350890+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHUK42AR","created_at":"2026-07-05T11:01:07.350890+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/GHUK42ARTMTROFTSY2H6PT4WZN","json":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN.json","graph_json":"https://pith.science/api/pith-number/GHUK42ARTMTROFTSY2H6PT4WZN/graph.json","events_json":"https://pith.science/api/pith-number/GHUK42ARTMTROFTSY2H6PT4WZN/events.json","paper":"https://pith.science/paper/GHUK42AR"},"agent_actions":{"view_html":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN","download_json":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN.json","view_paper":"https://pith.science/paper/GHUK42AR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06319&json=true","fetch_graph":"https://pith.science/api/pith-number/GHUK42ARTMTROFTSY2H6PT4WZN/graph.json","fetch_events":"https://pith.science/api/pith-number/GHUK42ARTMTROFTSY2H6PT4WZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/action/storage_attestation","attest_author":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/action/author_attestation","sign_citation":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/action/citation_signature","submit_replication":"https://pith.science/pith/GHUK42ARTMTROFTSY2H6PT4WZN/action/replication_record"}},"created_at":"2026-07-05T11:01:07.350890+00:00","updated_at":"2026-07-05T11:01:07.350890+00:00"}