{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T5M6SY4SVA2IPHGXY7CW2GAGUB","short_pith_number":"pith:T5M6SY4S","schema_version":"1.0","canonical_sha256":"9f59e96392a834879cd7c7c56d1806a0445357a72ca5ffdad5841fca100024f5","source":{"kind":"arxiv","id":"2412.00534","version":1},"attestation_state":"computed","paper":{"title":"Towards Fault Tolerance in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Danya Yao, Huaxin Pei, Liang Feng, Yi Zhang, Yuchen Shi","submitted_at":"2024-11-30T16:56:29Z","abstract_excerpt":"Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attentio"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.00534","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-30T16:56:29Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"554eeae9cb76c958de0c9648d673ad3f7ca590e14a88fe16b2f6197930ed9384","abstract_canon_sha256":"e1e6d5ebb466fdbd03f0c1be201407077e5c8943983c316d5d80fac240723c22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:43.287818Z","signature_b64":"ZJ9XXM/fWd2Isumjfw1J9Ip2yfljKH5D8vXKA5V0gVlZisLcd7iUUpQELToBpjCbppgtxn3FgVfvA/+hR52MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f59e96392a834879cd7c7c56d1806a0445357a72ca5ffdad5841fca100024f5","last_reissued_at":"2026-07-05T09:42:43.287221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:43.287221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fault Tolerance in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Danya Yao, Huaxin Pei, Liang Feng, Yi Zhang, Yuchen Shi","submitted_at":"2024-11-30T16:56:29Z","abstract_excerpt":"Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to extract critical information from the chaotic state space created by unexpected faults. Second, transitions recorded before and after faults in the replay buffer affect training unevenly, leading to a sample imbalance problem. To overcome these challenges, this paper enhances the fault tolerance of MARL by combining optimized model architecture with a tailored training data sampling strategy. Specifically, an attentio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00534","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.00534/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.00534","created_at":"2026-07-05T09:42:43.287282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00534v1","created_at":"2026-07-05T09:42:43.287282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00534","created_at":"2026-07-05T09:42:43.287282+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5M6SY4SVA2I","created_at":"2026-07-05T09:42:43.287282+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5M6SY4SVA2IPHGX","created_at":"2026-07-05T09:42:43.287282+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5M6SY4S","created_at":"2026-07-05T09:42:43.287282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.06684","citing_title":"Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB","json":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB.json","graph_json":"https://pith.science/api/pith-number/T5M6SY4SVA2IPHGXY7CW2GAGUB/graph.json","events_json":"https://pith.science/api/pith-number/T5M6SY4SVA2IPHGXY7CW2GAGUB/events.json","paper":"https://pith.science/paper/T5M6SY4S"},"agent_actions":{"view_html":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB","download_json":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB.json","view_paper":"https://pith.science/paper/T5M6SY4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00534&json=true","fetch_graph":"https://pith.science/api/pith-number/T5M6SY4SVA2IPHGXY7CW2GAGUB/graph.json","fetch_events":"https://pith.science/api/pith-number/T5M6SY4SVA2IPHGXY7CW2GAGUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB/action/storage_attestation","attest_author":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB/action/author_attestation","sign_citation":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB/action/citation_signature","submit_replication":"https://pith.science/pith/T5M6SY4SVA2IPHGXY7CW2GAGUB/action/replication_record"}},"created_at":"2026-07-05T09:42:43.287282+00:00","updated_at":"2026-07-05T09:42:43.287282+00:00"}