{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XT7ZR7UNLWSL65EHPMTC6QIVJT","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":"12cc01345608123ce6b977193651c1cdfd461183dfe9d1271806347286850468","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-27T20:14:28Z","title_canon_sha256":"9b74a43d8774af4ebfb97416a96fc62f699a6c4dcf43a6d77af7e7b7aea0f838"},"schema_version":"1.0","source":{"id":"2005.13625","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.13625","created_at":"2026-07-05T07:07:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.13625v8","created_at":"2026-07-05T07:07:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13625","created_at":"2026-07-05T07:07:01Z"},{"alias_kind":"pith_short_12","alias_value":"XT7ZR7UNLWSL","created_at":"2026-07-05T07:07:01Z"},{"alias_kind":"pith_short_16","alias_value":"XT7ZR7UNLWSL65EH","created_at":"2026-07-05T07:07:01Z"},{"alias_kind":"pith_short_8","alias_value":"XT7ZR7UN","created_at":"2026-07-05T07:07:01Z"}],"graph_snapshots":[{"event_id":"sha256:553b2629d4b23324f670093bfeda2b69ef3e8c9436d19b3027f76dab0720860e","target":"graph","created_at":"2026-07-05T07:07:01Z","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/2005.13625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Parameter sharing, where each agent independently learns a policy with fully shared parameters between all policies, is a popular baseline method for multi-agent deep reinforcement learning. Unfortunately, since all agents share the same policy network, they cannot learn different policies or tasks. This issue has been circumvented experimentally by adding an agent-specific indicator signal to observations, which we term \"agent indication\". Agent indication is limited, however, in that without modification it does not allow parameter sharing to be applied to environments where the action space","authors_text":"Aakriti Agrawal, Benjamin Black, J. K. Terry, Nathaniel Grammel, Sanghyun Son","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-27T20:14:28Z","title":"Revisiting Parameter Sharing in Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13625","kind":"arxiv","version":8},"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":"sha256:40b5d9c74329310cc8d3252e5fb5bab58c4239496bbc5102d6eba77c691e0703","target":"record","created_at":"2026-07-05T07:07:01Z","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":"12cc01345608123ce6b977193651c1cdfd461183dfe9d1271806347286850468","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-27T20:14:28Z","title_canon_sha256":"9b74a43d8774af4ebfb97416a96fc62f699a6c4dcf43a6d77af7e7b7aea0f838"},"schema_version":"1.0","source":{"id":"2005.13625","kind":"arxiv","version":8}},"canonical_sha256":"bcff98fe8d5da4bf74877b262f41154cf8ce34ce435b663d01b850cac49f2e2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcff98fe8d5da4bf74877b262f41154cf8ce34ce435b663d01b850cac49f2e2b","first_computed_at":"2026-07-05T07:07:01.870461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:01.870461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7knelAMvP3PwN+FB0aQ1xwH3Vk4HYt09Shp3IoVNgStyEjZ0RSryBfzMZsZAfMGcHxm+s+sRoGeb0l1eJ6nRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:01.870947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.13625","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b5d9c74329310cc8d3252e5fb5bab58c4239496bbc5102d6eba77c691e0703","sha256:553b2629d4b23324f670093bfeda2b69ef3e8c9436d19b3027f76dab0720860e"],"state_sha256":"8e52f2a7331c623a6aaede676a3c742542ba236d8f91dfc7c6915b1ee0af582b"}