{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FMZFCQGWNLVMWA5PAYHMSCHDRH","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":"3327de982f454d2534c232bf14de1b750e8e6ed7f090d5c659821b40d01061fc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-09T11:33:46Z","title_canon_sha256":"ec5292ac44ad6ef5c56337862387b8c4e41ef7ee38a7a7d8fce26cb327d75ea0"},"schema_version":"1.0","source":{"id":"2108.03952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03952","created_at":"2026-07-05T03:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03952v2","created_at":"2026-07-05T03:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03952","created_at":"2026-07-05T03:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"FMZFCQGWNLVM","created_at":"2026-07-05T03:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"FMZFCQGWNLVMWA5P","created_at":"2026-07-05T03:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"FMZFCQGW","created_at":"2026-07-05T03:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:92f5e241047d48c0870085955c85a0fad82644696402f0baef605748d02018d4","target":"graph","created_at":"2026-07-05T03:05:04Z","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/2108.03952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent control problems constitute an interesting area of application for deep reinforcement learning models with continuous action spaces. Such real-world applications, however, typically come with critical safety constraints that must not be violated. In order to ensure safety, we enhance the well-known multi-agent deep deterministic policy gradient (MADDPG) framework by adding a safety layer to the deep policy network. In particular, we extend the idea of linearizing the single-step transition dynamics, as was done for single-agent systems in Safe DDPG (Dalal et al., 2018), to multi-ag","authors_text":"Athina Nisioti, Dario Pavllo, Dimitris Gkouletsos, Jonas Kohler, Konstantinos Zisis, Ziyad Sheebaelhamd","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-09T11:33:46Z","title":"Safe Deep Reinforcement Learning for Multi-Agent Systems with Continuous Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03952","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:cb22fa7c9e5aea989ad59533ab389eab40af30cf794557a3e9f78705f86e2e08","target":"record","created_at":"2026-07-05T03:05:04Z","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":"3327de982f454d2534c232bf14de1b750e8e6ed7f090d5c659821b40d01061fc","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-08-09T11:33:46Z","title_canon_sha256":"ec5292ac44ad6ef5c56337862387b8c4e41ef7ee38a7a7d8fce26cb327d75ea0"},"schema_version":"1.0","source":{"id":"2108.03952","kind":"arxiv","version":2}},"canonical_sha256":"2b325140d66aeacb03af060ec908e389c95210a7731c2a5b53ceffb8abcf532d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b325140d66aeacb03af060ec908e389c95210a7731c2a5b53ceffb8abcf532d","first_computed_at":"2026-07-05T03:05:04.284064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:04.284064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4DHmQJfeMnL3s5FFMiNFfiiMMPkExJmf/qe66Ezl/er55YsM5UQhwSeOJb6O2qwY9xJSq2cDezVDGv3iIY/MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:04.284483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.03952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb22fa7c9e5aea989ad59533ab389eab40af30cf794557a3e9f78705f86e2e08","sha256:92f5e241047d48c0870085955c85a0fad82644696402f0baef605748d02018d4"],"state_sha256":"b72be99345b7e2dbb3cd70f715987f19ba3e04a4264c905a97cb10ab06574d45"}