{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NDKWDS7EIAT72WT2CDXCGBQDUB","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":"7928971303258b289c3c2b9c9a2d201ccfeca94748487256552e8f8f8736ca1e","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T19:37:01Z","title_canon_sha256":"20281de520c13844c317b32224b06a6910c72aab76be10c4cee1a7a2b22d249f"},"schema_version":"1.0","source":{"id":"2104.13446","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.13446","created_at":"2026-07-05T02:38:09Z"},{"alias_kind":"arxiv_version","alias_value":"2104.13446v2","created_at":"2026-07-05T02:38:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13446","created_at":"2026-07-05T02:38:09Z"},{"alias_kind":"pith_short_12","alias_value":"NDKWDS7EIAT7","created_at":"2026-07-05T02:38:09Z"},{"alias_kind":"pith_short_16","alias_value":"NDKWDS7EIAT72WT2","created_at":"2026-07-05T02:38:09Z"},{"alias_kind":"pith_short_8","alias_value":"NDKWDS7E","created_at":"2026-07-05T02:38:09Z"}],"graph_snapshots":[{"event_id":"sha256:6d7fdb98b057e93b0564f64421636e6f38de06ce6da5f067ffda816ee3eadab4","target":"graph","created_at":"2026-07-05T02:38:09Z","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/2104.13446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant performance gap between state-of-the-art policy gradient and value-based methods on the popular StarCraft Multi-Agent Challenge (SMAC) benchmark. In this paper, we introduce semi-on-policy (SOP) training as an effective and computationally efficient way to address the sample inefficiency of on-policy policy gradient methods. We enhance two state-of-the-art policy gradient algorithm","authors_text":"Bei Peng, Bozhidar Vasilev, Shimon Whiteson, Tarun Gupta","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T19:37:01Z","title":"Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13446","kind":"arxiv","version":2},"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":"sha256:9a2694df97e9f89d8d7e65f3a467de81478e6d8190fb5f9da4aedbe9cc870d38","target":"record","created_at":"2026-07-05T02:38:09Z","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":"7928971303258b289c3c2b9c9a2d201ccfeca94748487256552e8f8f8736ca1e","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-27T19:37:01Z","title_canon_sha256":"20281de520c13844c317b32224b06a6910c72aab76be10c4cee1a7a2b22d249f"},"schema_version":"1.0","source":{"id":"2104.13446","kind":"arxiv","version":2}},"canonical_sha256":"68d561cbe44027fd5a7a10ee230603a07a9bedab4faa5ef320fab93b373d7160","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68d561cbe44027fd5a7a10ee230603a07a9bedab4faa5ef320fab93b373d7160","first_computed_at":"2026-07-05T02:38:09.620554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:09.620554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TaZeVFVe9jSeM/gK/iyn04MNAonIF2F1gOSnPgmaPpr8/LF6S9KUbb+YcnbjFY2FUIF75T9JlX2rAZzZHqjLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:09.621023Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.13446","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a2694df97e9f89d8d7e65f3a467de81478e6d8190fb5f9da4aedbe9cc870d38","sha256:6d7fdb98b057e93b0564f64421636e6f38de06ce6da5f067ffda816ee3eadab4"],"state_sha256":"73f3094ff5a346b367d04a2c67231364740488d0a1004e830909ae21ca7b6dfb"}