{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:3R7T7N4J6PAQTKZEEUQZ7UTT6E","short_pith_number":"pith:3R7T7N4J","schema_version":"1.0","canonical_sha256":"dc7f3fb789f3c109ab2425219fd273f1190a18ae6ec3c1f79c38dd6ec354325c","source":{"kind":"arxiv","id":"2006.15223","version":1},"attestation_state":"computed","paper":{"title":"Perception-Prediction-Reaction Agents for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Stooke, Max Jaderberg, Siddhant M. Jayakumar, Valentin Dalibard, Wojciech M. Czarnecki","submitted_at":"2020-06-26T21:53:47Z","abstract_excerpt":"We introduce a new recurrent agent architecture and associated auxiliary losses which improve reinforcement learning in partially observable tasks requiring long-term memory. We employ a temporal hierarchy, using a slow-ticking recurrent core to allow information to flow more easily over long time spans, and three fast-ticking recurrent cores with connections designed to create an information asymmetry. The \\emph{reaction} core incorporates new observations with input from the slow core to produce the agent's policy; the \\emph{perception} core accesses only short-term observations and informs "},"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":"2006.15223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-06-26T21:53:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e74241cd8d18fa7207456aea3612a2a7373d9366fc616ba1a2fe2f78aab1839f","abstract_canon_sha256":"835295a56dd39a861ac7a4ac02ae14e78709adad95238045c9e9fd1b08e9b66d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:14:03.401349Z","signature_b64":"V6hrzFI5HU6Rx3M7+tL7G+Gl3Tx/uiuUjx/1IPgnN2msZi9Bp7S1u2lTP2HZ0TLYBRIRUKV2R0xG0c9cHDb6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc7f3fb789f3c109ab2425219fd273f1190a18ae6ec3c1f79c38dd6ec354325c","last_reissued_at":"2026-07-05T01:14:03.400984Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:14:03.400984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perception-Prediction-Reaction Agents for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Adam Stooke, Max Jaderberg, Siddhant M. Jayakumar, Valentin Dalibard, Wojciech M. Czarnecki","submitted_at":"2020-06-26T21:53:47Z","abstract_excerpt":"We introduce a new recurrent agent architecture and associated auxiliary losses which improve reinforcement learning in partially observable tasks requiring long-term memory. We employ a temporal hierarchy, using a slow-ticking recurrent core to allow information to flow more easily over long time spans, and three fast-ticking recurrent cores with connections designed to create an information asymmetry. The \\emph{reaction} core incorporates new observations with input from the slow core to produce the agent's policy; the \\emph{perception} core accesses only short-term observations and informs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15223","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/2006.15223/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":"2006.15223","created_at":"2026-07-05T01:14:03.401041+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.15223v1","created_at":"2026-07-05T01:14:03.401041+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15223","created_at":"2026-07-05T01:14:03.401041+00:00"},{"alias_kind":"pith_short_12","alias_value":"3R7T7N4J6PAQ","created_at":"2026-07-05T01:14:03.401041+00:00"},{"alias_kind":"pith_short_16","alias_value":"3R7T7N4J6PAQTKZE","created_at":"2026-07-05T01:14:03.401041+00:00"},{"alias_kind":"pith_short_8","alias_value":"3R7T7N4J","created_at":"2026-07-05T01:14:03.401041+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/3R7T7N4J6PAQTKZEEUQZ7UTT6E","json":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E.json","graph_json":"https://pith.science/api/pith-number/3R7T7N4J6PAQTKZEEUQZ7UTT6E/graph.json","events_json":"https://pith.science/api/pith-number/3R7T7N4J6PAQTKZEEUQZ7UTT6E/events.json","paper":"https://pith.science/paper/3R7T7N4J"},"agent_actions":{"view_html":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E","download_json":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E.json","view_paper":"https://pith.science/paper/3R7T7N4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.15223&json=true","fetch_graph":"https://pith.science/api/pith-number/3R7T7N4J6PAQTKZEEUQZ7UTT6E/graph.json","fetch_events":"https://pith.science/api/pith-number/3R7T7N4J6PAQTKZEEUQZ7UTT6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E/action/storage_attestation","attest_author":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E/action/author_attestation","sign_citation":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E/action/citation_signature","submit_replication":"https://pith.science/pith/3R7T7N4J6PAQTKZEEUQZ7UTT6E/action/replication_record"}},"created_at":"2026-07-05T01:14:03.401041+00:00","updated_at":"2026-07-05T01:14:03.401041+00:00"}