{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JRPW2CEDXJJEWPVGUIYAWM663U","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":"2245b6f106440840eff6debc864f7d6d16ce19c6d2ae831f25fbbe3c7818a1fe","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T13:57:11Z","title_canon_sha256":"9ea2553eb8cdf28dbc2bc329350cc746cc27177ae7622662cd16ff07bd4c813b"},"schema_version":"1.0","source":{"id":"2005.09453","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09453","created_at":"2026-07-05T01:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09453v2","created_at":"2026-07-05T01:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09453","created_at":"2026-07-05T01:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"JRPW2CEDXJJE","created_at":"2026-07-05T01:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"JRPW2CEDXJJEWPVG","created_at":"2026-07-05T01:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"JRPW2CED","created_at":"2026-07-05T01:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:b1c0a18b8e1244be18fa337946a29ddf4003d8a04a59d983a65a0737c7792b66","target":"graph","created_at":"2026-07-05T01:04:32Z","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/2005.09453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Exploration of the high-dimensional state action space is one of the biggest challenges in Reinforcement Learning (RL), especially in multi-agent domain. We present a novel technique called Experience Augmentation, which enables a time-efficient and boosted learning based on a fast, fair and thorough exploration to the environment. It can be combined with arbitrary off-policy MARL algorithms and is applicable to either homogeneous or heterogeneous environments. We demonstrate our approach by combining it with MADDPG and verifing the performance in two homogeneous and one heterogeneous environm","authors_text":"Bowei Yang, Guanghua Song, Shen Fan, Yining Chen, Zhenhui Ye","cross_cats":["cs.AI","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T13:57:11Z","title":"Experience Augmentation: Boosting and Accelerating Off-Policy Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09453","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":"sha256:58162c0674d386bf8c9d352e48236f473bbb6e4844009b73e848c473f76fe2df","target":"record","created_at":"2026-07-05T01:04:32Z","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":"2245b6f106440840eff6debc864f7d6d16ce19c6d2ae831f25fbbe3c7818a1fe","cross_cats_sorted":["cs.AI","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-19T13:57:11Z","title_canon_sha256":"9ea2553eb8cdf28dbc2bc329350cc746cc27177ae7622662cd16ff07bd4c813b"},"schema_version":"1.0","source":{"id":"2005.09453","kind":"arxiv","version":2}},"canonical_sha256":"4c5f6d0883ba524b3ea6a2300b33dedd272b04379077a1093dd0eadfb38ac81e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c5f6d0883ba524b3ea6a2300b33dedd272b04379077a1093dd0eadfb38ac81e","first_computed_at":"2026-07-05T01:04:32.666793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:04:32.666793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MUStDSWF7v05x7Wpf7zpyBB6u3j0Qm9wf+xzwWhetoc8AdiobfBiaHn06qZVXJzrqmL4R+MgKIX5LKF4CFgVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:04:32.667268Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09453","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58162c0674d386bf8c9d352e48236f473bbb6e4844009b73e848c473f76fe2df","sha256:b1c0a18b8e1244be18fa337946a29ddf4003d8a04a59d983a65a0737c7792b66"],"state_sha256":"202fa0f07e5676f963af2a43db6590561e874ef4acf5cedcb229f0ce141296b6"}