{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DVFFWQWRMOSUMDYAZOH32RUTN7","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":"42b86733a55007613821099b049b82aaaba31a1640dba00cdb11c3164230696d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T15:44:56Z","title_canon_sha256":"068d80b19a5d5bdcda34d58ffdad9cc59570c45f6b197c3a6c904826677a0e74"},"schema_version":"1.0","source":{"id":"2606.05021","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05021","created_at":"2026-06-04T01:10:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05021v1","created_at":"2026-06-04T01:10:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05021","created_at":"2026-06-04T01:10:02Z"},{"alias_kind":"pith_short_12","alias_value":"DVFFWQWRMOSU","created_at":"2026-06-04T01:10:02Z"},{"alias_kind":"pith_short_16","alias_value":"DVFFWQWRMOSUMDYA","created_at":"2026-06-04T01:10:02Z"},{"alias_kind":"pith_short_8","alias_value":"DVFFWQWR","created_at":"2026-06-04T01:10:02Z"}],"graph_snapshots":[{"event_id":"sha256:49b94ae59dc4a0a7636ea80e263186e3766d03d7c40919191d97de71c4836b08","target":"graph","created_at":"2026-06-04T01:10:02Z","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/2606.05021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate multi-agent deep reinforcement learning and propose two enhancements to the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm. First, we introduce a novel Action Inference mechanism that enables each agent to predict other agents' intended actions, thereby improving the accuracy and stability of its own policy. Second, we apply an importance sampling strategy, using geometric distribution, in the replay buffer to prioritize more recent and informative experiences, which helps mitigate the non-stationarity inherent in multi-agent environments. We evaluate both mod","authors_text":"Hamza Khan, Jason Liu, Marc Walden, Ryan Liu, Shaashwath Sivakumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T15:44:56Z","title":"Enhancing the MADDPG Algorithm for Multi-Agent Learning via Action Inference and Importance Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05021","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":"sha256:522517564b46e64ba87c5fc8b8ecae31b729ca3ebf14046a8eb58bb44497d678","target":"record","created_at":"2026-06-04T01:10:02Z","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":"42b86733a55007613821099b049b82aaaba31a1640dba00cdb11c3164230696d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T15:44:56Z","title_canon_sha256":"068d80b19a5d5bdcda34d58ffdad9cc59570c45f6b197c3a6c904826677a0e74"},"schema_version":"1.0","source":{"id":"2606.05021","kind":"arxiv","version":1}},"canonical_sha256":"1d4a5b42d163a5460f00cb8fbd46936fe7a52415e8cfe133b81315db1f2e2d04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d4a5b42d163a5460f00cb8fbd46936fe7a52415e8cfe133b81315db1f2e2d04","first_computed_at":"2026-06-04T01:10:02.431001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:10:02.431001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UHbvLSSTACmsGsayW2/ywKlI8aOXUDay0sdYJ6r/ybIqEsFlxEKmMPwny9RrKUTPtV06WSdQvdwDMQzpNBb0BA==","signature_status":"signed_v1","signed_at":"2026-06-04T01:10:02.431846Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05021","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:522517564b46e64ba87c5fc8b8ecae31b729ca3ebf14046a8eb58bb44497d678","sha256:49b94ae59dc4a0a7636ea80e263186e3766d03d7c40919191d97de71c4836b08"],"state_sha256":"49c9bbf523208ce4e3c9f9d2b80f32bdfa244cc29f495446cef10a66bf87658d"}