{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WIU2R4SJ5C43N7LPCS3FT5WDD6","short_pith_number":"pith:WIU2R4SJ","schema_version":"1.0","canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","source":{"kind":"arxiv","id":"1804.04577","version":3},"attestation_state":"computed","paper":{"title":"Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitri P. Bertsekas","submitted_at":"2018-04-12T15:46:12Z","abstract_excerpt":"In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller \"aggregate\" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines"},"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":"1804.04577","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-12T15:46:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"110212f82959808cb8dcebab2e5989f38fde11d9cde39cfa9ae965c3f358afa1","abstract_canon_sha256":"c68a610c24f0e49b81345d1561a19012044b4e636f92b091e4b9e759c9d9b20a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:32.646040Z","signature_b64":"+Lh2p8nrsgMekeFHWlHS1Y/tYHrOowVNAQPvhSHnNht74mWEh2PgycY3CZT23yt2gO7Po6xVzlsaiCLr34JBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","last_reissued_at":"2026-05-18T00:07:32.645474Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:32.645474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dimitri P. Bertsekas","submitted_at":"2018-04-12T15:46:12Z","abstract_excerpt":"In this paper we discuss policy iteration methods for approximate solution of a finite-state discounted Markov decision problem, with a focus on feature-based aggregation methods and their connection with deep reinforcement learning schemes. We introduce features of the states of the original problem, and we formulate a smaller \"aggregate\" Markov decision problem, whose states relate to the features. We discuss properties and possible implementations of this type of aggregation, including a new approach to approximate policy iteration. In this approach the policy improvement operation combines"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04577","kind":"arxiv","version":3},"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":"1804.04577","created_at":"2026-05-18T00:07:32.645571+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.04577v3","created_at":"2026-05-18T00:07:32.645571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04577","created_at":"2026-05-18T00:07:32.645571+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIU2R4SJ5C43","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIU2R4SJ5C43N7LP","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIU2R4SJ","created_at":"2026-05-18T12:32:59.047623+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/WIU2R4SJ5C43N7LPCS3FT5WDD6","json":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6.json","graph_json":"https://pith.science/api/pith-number/WIU2R4SJ5C43N7LPCS3FT5WDD6/graph.json","events_json":"https://pith.science/api/pith-number/WIU2R4SJ5C43N7LPCS3FT5WDD6/events.json","paper":"https://pith.science/paper/WIU2R4SJ"},"agent_actions":{"view_html":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6","download_json":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6.json","view_paper":"https://pith.science/paper/WIU2R4SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.04577&json=true","fetch_graph":"https://pith.science/api/pith-number/WIU2R4SJ5C43N7LPCS3FT5WDD6/graph.json","fetch_events":"https://pith.science/api/pith-number/WIU2R4SJ5C43N7LPCS3FT5WDD6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/action/storage_attestation","attest_author":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/action/author_attestation","sign_citation":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/action/citation_signature","submit_replication":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/action/replication_record"}},"created_at":"2026-05-18T00:07:32.645571+00:00","updated_at":"2026-05-18T00:07:32.645571+00:00"}