{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WIU2R4SJ5C43N7LPCS3FT5WDD6","short_pith_number":"pith:WIU2R4SJ","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"},"canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","source":{"kind":"arxiv","id":"1804.04577","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WIU2R4SJ5C43N7LPCS3FT5WDD6","target":"record","payload":{"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"},"canonical_sha256":"b229a8f249e8b9b6fd6f14b659f6c31f8bebe8334e4d11ada3a8e30509145a8e","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"},"source_kind":"arxiv","source_id":"1804.04577","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3i6G+Mj38wdV/zF9kY2f2FT3x/sS/sgdtyFcb3szihLhEmKs5B+cKtcmpo2VZq+txayjEk7OW7m/AjVsdJyDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:47:44.887478Z"},"content_sha256":"b098cd7144a05bc327c3fb8e6beb14b525a4b1a0646e6ffcf43d0d42381acafe","schema_version":"1.0","event_id":"sha256:b098cd7144a05bc327c3fb8e6beb14b525a4b1a0646e6ffcf43d0d42381acafe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WIU2R4SJ5C43N7LPCS3FT5WDD6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08DrXv8RnEPUusGbQ2wRRrP2phtSVUObJir3S9uzhDzcPwOU0rWjUS3WPZ71UGeWdhS6BcdGkJeLs2j+mFs9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T09:47:44.887833Z"},"content_sha256":"33e15468f479d5a62a6aa2cd5a33b5fbfd1f3afd23d0d9dabf93e529e1b959e1","schema_version":"1.0","event_id":"sha256:33e15468f479d5a62a6aa2cd5a33b5fbfd1f3afd23d0d9dabf93e529e1b959e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/bundle.json","state_url":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T09:47:44Z","links":{"resolver":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6","bundle":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/bundle.json","state":"https://pith.science/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIU2R4SJ5C43N7LPCS3FT5WDD6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTxguN02TFOvb64oDo5XSrqQ1CosbNEHkra+t69djgpuK8kquhkjGjahdhblJSPQXtDo/zabxaTfhEDHFCnIAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T09:47:44.889810Z","bundle_sha256":"4c84565d2ed62539f8c9fd72636c9c3f5839ded17593e27be1d3aa7050773a38"}}