{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LUQYN5UBAFVXFKWPJWTMBHHORF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"52cf10096b4be2db1d953352ae761706b8d4cfa55046df9ce9a4f334ed753aeb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:49Z","title_canon_sha256":"d7694141ffc6070477f82dd0d8c7b5abfb6ce07444dce97c9baa32d5a5fef556"},"schema_version":"1.0","source":{"id":"2302.04376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.04376","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"arxiv_version","alias_value":"2302.04376v1","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04376","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_12","alias_value":"LUQYN5UBAFVX","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_16","alias_value":"LUQYN5UBAFVXFKWP","created_at":"2026-07-05T05:40:13Z"},{"alias_kind":"pith_short_8","alias_value":"LUQYN5UB","created_at":"2026-07-05T05:40:13Z"}],"graph_snapshots":[{"event_id":"sha256:e49f3c1876d5edbeb0f60875783c619605fb0bfb7a0383e2a56c98872ead8a59","target":"graph","created_at":"2026-07-05T05:40:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.04376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Csaba Szepesv\\'ari, Ilija Bogunovic, Johannes Kirschner, Matej Jusup, Seyed Alireza Bakhtiari, Volodymyr Tkachuk","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:49Z","title":"Efficient Planning in Combinatorial Action Spaces with Applications to Cooperative Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04376","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:997ed09273e8d22d328723f022079044282a5e81280169901fec04495d010d8a","target":"record","created_at":"2026-07-05T05:40:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"52cf10096b4be2db1d953352ae761706b8d4cfa55046df9ce9a4f334ed753aeb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-08T23:42:49Z","title_canon_sha256":"d7694141ffc6070477f82dd0d8c7b5abfb6ce07444dce97c9baa32d5a5fef556"},"schema_version":"1.0","source":{"id":"2302.04376","kind":"arxiv","version":1}},"canonical_sha256":"5d2186f681016b72aacf4da6c09cee8954b6d459c22d4fef0110af52416e8ad8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d2186f681016b72aacf4da6c09cee8954b6d459c22d4fef0110af52416e8ad8","first_computed_at":"2026-07-05T05:40:13.193338Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:40:13.193338Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+/G3WHMEpIrb/hTg8aD8qNidNDvCid/bWrTLUaRl8CCXsBL6dA4lloSJ/NHI8t9Ceh5w7IohtO+nOMH9bOZPAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:40:13.193791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.04376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:997ed09273e8d22d328723f022079044282a5e81280169901fec04495d010d8a","sha256:e49f3c1876d5edbeb0f60875783c619605fb0bfb7a0383e2a56c98872ead8a59"],"state_sha256":"95d78835a894c57895447a6205ee0934732395c82d3289b9fec1a8563ad44087"}