{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OUANY4VJ6N73HZUF274DBIDRMD","short_pith_number":"pith:OUANY4VJ","schema_version":"1.0","canonical_sha256":"7500dc72a9f37fb3e685d7f830a07160eb82c1a999feefeb1500f93e90c1dc75","source":{"kind":"arxiv","id":"1911.07643","version":4},"attestation_state":"computed","paper":{"title":"Influence-aware Memory Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksander Czechowski, Elena Congeduti, Frans A. Oliehoek, Jinke He, Miguel Suau, Rolf A.N. Starre","submitted_at":"2019-11-18T13:54:25Z","abstract_excerpt":"Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize past observations. However, these models are expensive to train and have convergence difficulties, especially when dealing with high dimensional input spaces. In this paper, we propose influence-aware memory (IAM), a theoretically inspired memory architecture that tries to alleviate"},"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":"1911.07643","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-18T13:54:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f2da4823a76bcc4b6d6ac2297666c45da4beaef5f71a0373b9f9dd50c8d22e60","abstract_canon_sha256":"b393449910adcd76f3ffc7e1a50bd6cb381ecbcd5da970f4c7ffb9e19378abc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:56.476791Z","signature_b64":"e5mzgOjeMphmfWzxl5Ks19zDW6VCdACHLo2swscVaEj0utrxhOn5jA5xzIfvE78DIX3AMRwe/YxkwMJ2mwBzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7500dc72a9f37fb3e685d7f830a07160eb82c1a999feefeb1500f93e90c1dc75","last_reissued_at":"2026-07-05T02:15:56.476384Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:56.476384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Influence-aware Memory Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksander Czechowski, Elena Congeduti, Frans A. Oliehoek, Jinke He, Miguel Suau, Rolf A.N. Starre","submitted_at":"2019-11-18T13:54:25Z","abstract_excerpt":"Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize past observations. However, these models are expensive to train and have convergence difficulties, especially when dealing with high dimensional input spaces. In this paper, we propose influence-aware memory (IAM), a theoretically inspired memory architecture that tries to alleviate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07643","kind":"arxiv","version":4},"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/1911.07643/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":"1911.07643","created_at":"2026-07-05T02:15:56.476447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.07643v4","created_at":"2026-07-05T02:15:56.476447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07643","created_at":"2026-07-05T02:15:56.476447+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUANY4VJ6N73","created_at":"2026-07-05T02:15:56.476447+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUANY4VJ6N73HZUF","created_at":"2026-07-05T02:15:56.476447+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUANY4VJ","created_at":"2026-07-05T02:15:56.476447+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/OUANY4VJ6N73HZUF274DBIDRMD","json":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD.json","graph_json":"https://pith.science/api/pith-number/OUANY4VJ6N73HZUF274DBIDRMD/graph.json","events_json":"https://pith.science/api/pith-number/OUANY4VJ6N73HZUF274DBIDRMD/events.json","paper":"https://pith.science/paper/OUANY4VJ"},"agent_actions":{"view_html":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD","download_json":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD.json","view_paper":"https://pith.science/paper/OUANY4VJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.07643&json=true","fetch_graph":"https://pith.science/api/pith-number/OUANY4VJ6N73HZUF274DBIDRMD/graph.json","fetch_events":"https://pith.science/api/pith-number/OUANY4VJ6N73HZUF274DBIDRMD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD/action/storage_attestation","attest_author":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD/action/author_attestation","sign_citation":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD/action/citation_signature","submit_replication":"https://pith.science/pith/OUANY4VJ6N73HZUF274DBIDRMD/action/replication_record"}},"created_at":"2026-07-05T02:15:56.476447+00:00","updated_at":"2026-07-05T02:15:56.476447+00:00"}