{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:X2SA4KXK27NECYWWLN36KNG6N7","short_pith_number":"pith:X2SA4KXK","schema_version":"1.0","canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","source":{"kind":"arxiv","id":"2210.16915","version":1},"attestation_state":"computed","paper":{"title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Thanh H. Nguyen, The Viet Bui, Tien Mai","submitted_at":"2022-10-30T18:32:02Z","abstract_excerpt":"Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach; knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In t"},"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":"2210.16915","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-30T18:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"22ccdc4de660b8bab5aa3f8a234357e4bc17a37446940e9180f912d82ee9b20e","abstract_canon_sha256":"a0176caa8c38ce0702973040c1ff901205c05f630b563afabd4b17bfb4a5691e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:52.444949Z","signature_b64":"VmWk40WpjKRzPFoK2kBxsqjvbpt5wEmwlQEiq/zkQ/5q3yuhblZoigubs1w4L+R10j2Hyf8RFT08xwoHxK7WDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bea40e2aead7da4162d65b77e534de6fe19f003546f8165283e80e9b8ce61af5","last_reissued_at":"2026-07-05T05:11:52.444488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:52.444488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imitating Opponent to Win: Adversarial Policy Imitation Learning in Two-player Competitive Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Thanh H. Nguyen, The Viet Bui, Tien Mai","submitted_at":"2022-10-30T18:32:02Z","abstract_excerpt":"Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach; knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16915","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/2210.16915/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":"2210.16915","created_at":"2026-07-05T05:11:52.444551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.16915v1","created_at":"2026-07-05T05:11:52.444551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16915","created_at":"2026-07-05T05:11:52.444551+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2SA4KXK27NE","created_at":"2026-07-05T05:11:52.444551+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2SA4KXK27NECYWW","created_at":"2026-07-05T05:11:52.444551+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2SA4KXK","created_at":"2026-07-05T05:11:52.444551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7","json":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7.json","graph_json":"https://pith.science/api/pith-number/X2SA4KXK27NECYWWLN36KNG6N7/graph.json","events_json":"https://pith.science/api/pith-number/X2SA4KXK27NECYWWLN36KNG6N7/events.json","paper":"https://pith.science/paper/X2SA4KXK"},"agent_actions":{"view_html":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7","download_json":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7.json","view_paper":"https://pith.science/paper/X2SA4KXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.16915&json=true","fetch_graph":"https://pith.science/api/pith-number/X2SA4KXK27NECYWWLN36KNG6N7/graph.json","fetch_events":"https://pith.science/api/pith-number/X2SA4KXK27NECYWWLN36KNG6N7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/action/storage_attestation","attest_author":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/action/author_attestation","sign_citation":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/action/citation_signature","submit_replication":"https://pith.science/pith/X2SA4KXK27NECYWWLN36KNG6N7/action/replication_record"}},"created_at":"2026-07-05T05:11:52.444551+00:00","updated_at":"2026-07-05T05:11:52.444551+00:00"}