{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WIU2R4SJ5C43N7LPCS3FT5WDD6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c68a610c24f0e49b81345d1561a19012044b4e636f92b091e4b9e759c9d9b20a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-12T15:46:12Z","title_canon_sha256":"110212f82959808cb8dcebab2e5989f38fde11d9cde39cfa9ae965c3f358afa1"},"schema_version":"1.0","source":{"id":"1804.04577","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04577","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04577v3","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04577","created_at":"2026-05-18T00:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"WIU2R4SJ5C43","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"WIU2R4SJ5C43N7LP","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"WIU2R4SJ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:33e15468f479d5a62a6aa2cd5a33b5fbfd1f3afd23d0d9dabf93e529e1b959e1","target":"graph","created_at":"2026-05-18T00:07:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Dimitri P. Bertsekas","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-12T15:46:12Z","title":"Feature-Based Aggregation and Deep Reinforcement Learning: A Survey and Some New Implementations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04577","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b098cd7144a05bc327c3fb8e6beb14b525a4b1a0646e6ffcf43d0d42381acafe","target":"record","created_at":"2026-05-18T00:07:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c68a610c24f0e49b81345d1561a19012044b4e636f92b091e4b9e759c9d9b20a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-12T15:46:12Z","title_canon_sha256":"110212f82959808cb8dcebab2e5989f38fde11d9cde39cfa9ae965c3f358afa1"},"schema_version":"1.0","source":{"id":"1804.04577","kind":"arxiv","version":3}},"canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","first_computed_at":"2026-05-18T00:07:32.645474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:32.645474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Lh2p8nrsgMekeFHWlHS1Y/tYHrOowVNAQPvhSHnNht74mWEh2PgycY3CZT23yt2gO7Po6xVzlsaiCLr34JBDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:32.646040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04577","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b098cd7144a05bc327c3fb8e6beb14b525a4b1a0646e6ffcf43d0d42381acafe","sha256:33e15468f479d5a62a6aa2cd5a33b5fbfd1f3afd23d0d9dabf93e529e1b959e1"],"state_sha256":"d265b2cb992f9fa2bea7a638053623da2ecedb055e30fed3558df6361df384f9"}