{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YZSVZQHIYMSQYGP3CTW52IBSEW","short_pith_number":"pith:YZSVZQHI","schema_version":"1.0","canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","source":{"kind":"arxiv","id":"2306.07408","version":1},"attestation_state":"computed","paper":{"title":"Robust Reinforcement Learning through Efficient Adversarial Herding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao-Lun Hsu, Juncheng Dong, Miroslav Pajic, Qitong Gao, Vahid Tarokh","submitted_at":"2023-06-12T20:21:40Z","abstract_excerpt":"Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe performance degradation when the environment is exposed to potential disturbances. Adversarial training using a two-player max-min game has been proven effective in enhancing the robustness of RL agents. In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\\textit{i}$) the difficulty of the inner optimization problem, and ($\\texti"},"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":"2306.07408","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T20:21:40Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"e64d6ab4ee10bfb1ad7285ef01b19f4c92e2874af34aa652b94433aa41a8729b","abstract_canon_sha256":"f0f8fff28e27a802bf41185ac13e306fdf5d5c342bf42c11589633184b55c952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:03.660387Z","signature_b64":"KSI/8hPmC1FJDlJKzxB2nkNxb+upPll55uy478PHYTq1SetTPDD2+v6cXm1o3gIvBNmwipyLXb0kDeD5b0cdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6655cc0e8c3250c19fb14eddd203225b85bc58b8442e40d72b5c50b5762422c","last_reissued_at":"2026-07-05T06:20:03.659914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:03.659914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Reinforcement Learning through Efficient Adversarial Herding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Hao-Lun Hsu, Juncheng Dong, Miroslav Pajic, Qitong Gao, Vahid Tarokh","submitted_at":"2023-06-12T20:21:40Z","abstract_excerpt":"Although reinforcement learning (RL) is considered the gold standard for policy design, it may not always provide a robust solution in various scenarios. This can result in severe performance degradation when the environment is exposed to potential disturbances. Adversarial training using a two-player max-min game has been proven effective in enhancing the robustness of RL agents. In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\\textit{i}$) the difficulty of the inner optimization problem, and ($\\texti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07408","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/2306.07408/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":"2306.07408","created_at":"2026-07-05T06:20:03.659967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07408v1","created_at":"2026-07-05T06:20:03.659967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07408","created_at":"2026-07-05T06:20:03.659967+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZSVZQHIYMSQ","created_at":"2026-07-05T06:20:03.659967+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZSVZQHIYMSQYGP3","created_at":"2026-07-05T06:20:03.659967+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZSVZQHI","created_at":"2026-07-05T06:20:03.659967+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.02743","citing_title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW","json":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW.json","graph_json":"https://pith.science/api/pith-number/YZSVZQHIYMSQYGP3CTW52IBSEW/graph.json","events_json":"https://pith.science/api/pith-number/YZSVZQHIYMSQYGP3CTW52IBSEW/events.json","paper":"https://pith.science/paper/YZSVZQHI"},"agent_actions":{"view_html":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW","download_json":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW.json","view_paper":"https://pith.science/paper/YZSVZQHI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07408&json=true","fetch_graph":"https://pith.science/api/pith-number/YZSVZQHIYMSQYGP3CTW52IBSEW/graph.json","fetch_events":"https://pith.science/api/pith-number/YZSVZQHIYMSQYGP3CTW52IBSEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/action/storage_attestation","attest_author":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/action/author_attestation","sign_citation":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/action/citation_signature","submit_replication":"https://pith.science/pith/YZSVZQHIYMSQYGP3CTW52IBSEW/action/replication_record"}},"created_at":"2026-07-05T06:20:03.659967+00:00","updated_at":"2026-07-05T06:20:03.659967+00:00"}