{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5LNSAYFFO2FUZFR53FUAPUODKR","short_pith_number":"pith:5LNSAYFF","schema_version":"1.0","canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","source":{"kind":"arxiv","id":"1803.01489","version":1},"attestation_state":"computed","paper":{"title":"Recurrent Predictive State Policy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmed Hefny, Geoffrey Gordon, Siddhartha Srinivasa, Wen Sun, Zita Marinho","submitted_at":"2018-03-05T03:59:48Z","abstract_excerpt":"We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward. The recursive filter leverages predictive state representations (PSRs) (Rosencrantz and Gordon, 2004; Sun et al., 2016) by modeling predictive state-- a predictio"},"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":"1803.01489","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-03-05T03:59:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c4e2df910b29f1b44542bcd9a244ac2774e9a6fa90d3ca4c581201edd1d02db2","abstract_canon_sha256":"2662f4e6b09db08d29441bfdc47eece3705993aaccdd2d9fdf44265e4cd7bb5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:00.513401Z","signature_b64":"GPmk2zGKXKZ0zbGQ2Q6EWOIoUypB9EJ590bp683O9eJXfYb/Fu180LdCOz78bdrGd7nrEAGFcS9ZYZs0I+5hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eadb2060a5768b4c963dd96807d1c35461c6b51e7811109c38ea6fb48471bc6f","last_reissued_at":"2026-05-18T00:22:00.512870Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:00.512870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Recurrent Predictive State Policy Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Ahmed Hefny, Geoffrey Gordon, Siddhartha Srinivasa, Wen Sun, Zita Marinho","submitted_at":"2018-03-05T03:59:48Z","abstract_excerpt":"We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the state of the environment, and a reactive policy that directly maps beliefs to actions, to maximize the cumulative reward. The recursive filter leverages predictive state representations (PSRs) (Rosencrantz and Gordon, 2004; Sun et al., 2016) by modeling predictive state-- a predictio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01489","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":"1803.01489","created_at":"2026-05-18T00:22:00.512946+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.01489v1","created_at":"2026-05-18T00:22:00.512946+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01489","created_at":"2026-05-18T00:22:00.512946+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LNSAYFFO2FU","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LNSAYFFO2FUZFR5","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LNSAYFF","created_at":"2026-05-18T12:32:08.215937+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09671","citing_title":"Belief-State RWKV for Reinforcement Learning under Partial Observability","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR","json":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR.json","graph_json":"https://pith.science/api/pith-number/5LNSAYFFO2FUZFR53FUAPUODKR/graph.json","events_json":"https://pith.science/api/pith-number/5LNSAYFFO2FUZFR53FUAPUODKR/events.json","paper":"https://pith.science/paper/5LNSAYFF"},"agent_actions":{"view_html":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR","download_json":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR.json","view_paper":"https://pith.science/paper/5LNSAYFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.01489&json=true","fetch_graph":"https://pith.science/api/pith-number/5LNSAYFFO2FUZFR53FUAPUODKR/graph.json","fetch_events":"https://pith.science/api/pith-number/5LNSAYFFO2FUZFR53FUAPUODKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/action/storage_attestation","attest_author":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/action/author_attestation","sign_citation":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/action/citation_signature","submit_replication":"https://pith.science/pith/5LNSAYFFO2FUZFR53FUAPUODKR/action/replication_record"}},"created_at":"2026-05-18T00:22:00.512946+00:00","updated_at":"2026-05-18T00:22:00.512946+00:00"}