{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5WE5E65ATXUTIODUNR3IB7AKIL","short_pith_number":"pith:5WE5E65A","schema_version":"1.0","canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","source":{"kind":"arxiv","id":"2406.09976","version":2},"attestation_state":"computed","paper":{"title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Anwar, Siegfried Mercelis, Siemen Herremans","submitted_at":"2024-06-14T12:37:08Z","abstract_excerpt":"Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an a"},"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":"2406.09976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-14T12:37:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"274cd9978ea2f5e623396cdf88382e5bfe0a8f86bcdb4e19fdc7323bf1cae555","abstract_canon_sha256":"41d04bab55ff3eacd1a90d6fc5178d2530d3698634794ec250325f61451bdeef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:38.664741Z","signature_b64":"AHptIEUcveUnUTmwPYunUEQkZE1Qx8BSS5YkIz1FdCfwn87A7JJXmwpziRx7o/fspV4Qynf75M2A882Xf/q9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed89d27ba09de93438746c7680fc0a42c6fba9100db808b043fc9e0cc942c3d6","last_reissued_at":"2026-07-05T08:38:38.664113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:38.664113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Model-Based Reinforcement Learning with an Adversarial Auxiliary Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Anwar, Siegfried Mercelis, Siemen Herremans","submitted_at":"2024-06-14T12:37:08Z","abstract_excerpt":"Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and safety in the learned policies. More specifically, an RL agent that trains in a certain Markov decision process (MDP) often struggles to perform well in nearly identical MDPs. To address this issue, we employ the framework of Robust MDPs (RMDPs) in a model-based setting and introduce a novel learned transition model. Our method specifically incorporates an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09976","kind":"arxiv","version":2},"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/2406.09976/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":"2406.09976","created_at":"2026-07-05T08:38:38.664168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09976v2","created_at":"2026-07-05T08:38:38.664168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09976","created_at":"2026-07-05T08:38:38.664168+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WE5E65ATXUT","created_at":"2026-07-05T08:38:38.664168+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WE5E65ATXUTIODU","created_at":"2026-07-05T08:38:38.664168+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WE5E65A","created_at":"2026-07-05T08:38:38.664168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02844","citing_title":"Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL","json":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL.json","graph_json":"https://pith.science/api/pith-number/5WE5E65ATXUTIODUNR3IB7AKIL/graph.json","events_json":"https://pith.science/api/pith-number/5WE5E65ATXUTIODUNR3IB7AKIL/events.json","paper":"https://pith.science/paper/5WE5E65A"},"agent_actions":{"view_html":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL","download_json":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL.json","view_paper":"https://pith.science/paper/5WE5E65A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09976&json=true","fetch_graph":"https://pith.science/api/pith-number/5WE5E65ATXUTIODUNR3IB7AKIL/graph.json","fetch_events":"https://pith.science/api/pith-number/5WE5E65ATXUTIODUNR3IB7AKIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/action/storage_attestation","attest_author":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/action/author_attestation","sign_citation":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/action/citation_signature","submit_replication":"https://pith.science/pith/5WE5E65ATXUTIODUNR3IB7AKIL/action/replication_record"}},"created_at":"2026-07-05T08:38:38.664168+00:00","updated_at":"2026-07-05T08:38:38.664168+00:00"}