{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LUQYN5UBAFVXFKWPJWTMBHHORF","short_pith_number":"pith:LUQYN5UB","schema_version":"1.0","canonical_sha256":"5d2186f681016b72aacf4da6c09cee8954b6d459c22d4fef0110af52416e8ad8","source":{"kind":"arxiv","id":"2302.04376","version":1},"attestation_state":"computed","paper":{"title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Ilija Bogunovic, Johannes Kirschner, Matej Jusup, Seyed Alireza Bakhtiari, Volodymyr Tkachuk","submitted_at":"2023-02-08T23:42:49Z","abstract_excerpt":"A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly optimize a global reward function, which leads to a combinatorial blow-up in the action space by the number of agents. As a minimal requirement, we assume access to an argmax oracle that allows to efficiently compute the greedy policy for any Q-function in the model class. Building on recent work in planning with local access to a simulator and linear function ap"},"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":"2302.04376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d7694141ffc6070477f82dd0d8c7b5abfb6ce07444dce97c9baa32d5a5fef556","abstract_canon_sha256":"52cf10096b4be2db1d953352ae761706b8d4cfa55046df9ce9a4f334ed753aeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:13.193791Z","signature_b64":"+/G3WHMEpIrb/hTg8aD8qNidNDvCid/bWrTLUaRl8CCXsBL6dA4lloSJ/NHI8t9Ceh5w7IohtO+nOMH9bOZPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d2186f681016b72aacf4da6c09cee8954b6d459c22d4fef0110af52416e8ad8","last_reissued_at":"2026-07-05T05:40:13.193338Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:13.193338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Csaba Szepesv\\'ari, Ilija Bogunovic, Johannes Kirschner, Matej Jusup, Seyed Alireza Bakhtiari, Volodymyr Tkachuk","submitted_at":"2023-02-08T23:42:49Z","abstract_excerpt":"A practical challenge in reinforcement learning are combinatorial action spaces that make planning computationally demanding. For example, in cooperative multi-agent reinforcement learning, a potentially large number of agents jointly optimize a global reward function, which leads to a combinatorial blow-up in the action space by the number of agents. As a minimal requirement, we assume access to an argmax oracle that allows to efficiently compute the greedy policy for any Q-function in the model class. Building on recent work in planning with local access to a simulator and linear function ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04376","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/2302.04376/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":"2302.04376","created_at":"2026-07-05T05:40:13.193401+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04376v1","created_at":"2026-07-05T05:40:13.193401+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04376","created_at":"2026-07-05T05:40:13.193401+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUQYN5UBAFVX","created_at":"2026-07-05T05:40:13.193401+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUQYN5UBAFVXFKWP","created_at":"2026-07-05T05:40:13.193401+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUQYN5UB","created_at":"2026-07-05T05:40:13.193401+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/LUQYN5UBAFVXFKWPJWTMBHHORF","json":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF.json","graph_json":"https://pith.science/api/pith-number/LUQYN5UBAFVXFKWPJWTMBHHORF/graph.json","events_json":"https://pith.science/api/pith-number/LUQYN5UBAFVXFKWPJWTMBHHORF/events.json","paper":"https://pith.science/paper/LUQYN5UB"},"agent_actions":{"view_html":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF","download_json":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF.json","view_paper":"https://pith.science/paper/LUQYN5UB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04376&json=true","fetch_graph":"https://pith.science/api/pith-number/LUQYN5UBAFVXFKWPJWTMBHHORF/graph.json","fetch_events":"https://pith.science/api/pith-number/LUQYN5UBAFVXFKWPJWTMBHHORF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF/action/storage_attestation","attest_author":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF/action/author_attestation","sign_citation":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF/action/citation_signature","submit_replication":"https://pith.science/pith/LUQYN5UBAFVXFKWPJWTMBHHORF/action/replication_record"}},"created_at":"2026-07-05T05:40:13.193401+00:00","updated_at":"2026-07-05T05:40:13.193401+00:00"}