{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GOZGUW4CGPGNGXYNJF44GFENEZ","short_pith_number":"pith:GOZGUW4C","schema_version":"1.0","canonical_sha256":"33b26a5b8233ccd35f0d4979c3148d265b245b1360b28a077999571ff1c4bb26","source":{"kind":"arxiv","id":"1906.02500","version":1},"attestation_state":"computed","paper":{"title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Mott, Daan Wierstra, Daniel Zoran, Danilo J. Rezende, Mike Chrzanowski","submitted_at":"2019-06-06T10:02:52Z","abstract_excerpt":"Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially querying its view of the environment. The output of the attention mechanism allows direct observation of the information used by the agent to select its actions, enabling easier interpretation of this model than of traditional models. We analyze different strategies that the agents "},"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":"1906.02500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-06T10:02:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b392f64493a95f4bcb2ef22dc56b7479cbf03d2e59b8df6124eeebe9bf81c665","abstract_canon_sha256":"b9d1b7a12d752209c5984566030acdd39c40bf3be607677c15482723db92cc10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:00.968725Z","signature_b64":"N4PRVhMnVOrHK7IxUdk60dsLZaInNXtm3p/FEKqxr2Gr3NZ7E1ita3XK1XAGA2mjLO5PrQ8XzeaRTgtiuR9DAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33b26a5b8233ccd35f0d4979c3148d265b245b1360b28a077999571ff1c4bb26","last_reissued_at":"2026-05-17T23:44:00.968029Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:00.968029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Mott, Daan Wierstra, Daniel Zoran, Danilo J. Rezende, Mike Chrzanowski","submitted_at":"2019-06-06T10:02:52Z","abstract_excerpt":"Inspired by recent work in attention models for image captioning and question answering, we present a soft attention model for the reinforcement learning domain. This model uses a soft, top-down attention mechanism to create a bottleneck in the agent, forcing it to focus on task-relevant information by sequentially querying its view of the environment. The output of the attention mechanism allows direct observation of the information used by the agent to select its actions, enabling easier interpretation of this model than of traditional models. We analyze different strategies that the agents "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02500","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":""},"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":"1906.02500","created_at":"2026-05-17T23:44:00.968131+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02500v1","created_at":"2026-05-17T23:44:00.968131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02500","created_at":"2026-05-17T23:44:00.968131+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOZGUW4CGPGN","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOZGUW4CGPGNGXYN","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOZGUW4C","created_at":"2026-05-18T12:33:18.533446+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/GOZGUW4CGPGNGXYNJF44GFENEZ","json":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ.json","graph_json":"https://pith.science/api/pith-number/GOZGUW4CGPGNGXYNJF44GFENEZ/graph.json","events_json":"https://pith.science/api/pith-number/GOZGUW4CGPGNGXYNJF44GFENEZ/events.json","paper":"https://pith.science/paper/GOZGUW4C"},"agent_actions":{"view_html":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ","download_json":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ.json","view_paper":"https://pith.science/paper/GOZGUW4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02500&json=true","fetch_graph":"https://pith.science/api/pith-number/GOZGUW4CGPGNGXYNJF44GFENEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GOZGUW4CGPGNGXYNJF44GFENEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ/action/storage_attestation","attest_author":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ/action/author_attestation","sign_citation":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ/action/citation_signature","submit_replication":"https://pith.science/pith/GOZGUW4CGPGNGXYNJF44GFENEZ/action/replication_record"}},"created_at":"2026-05-17T23:44:00.968131+00:00","updated_at":"2026-05-17T23:44:00.968131+00:00"}