{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IGBK7G4JMNHIAQJ4BBVXQ5R6JF","short_pith_number":"pith:IGBK7G4J","canonical_record":{"source":{"id":"1802.09646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f2140084943a2445a66163cdd3e943197f4c4064b7c4d19af6c353b810d6369","abstract_canon_sha256":"a8135576c14eee229d0e5c46c76de67a0463c3a85aad6411f911095723810d07"},"schema_version":"1.0"},"canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","source":{"kind":"arxiv","id":"1802.09646","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09646","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09646v1","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09646","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"IGBK7G4JMNHI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IGBK7G4JMNHIAQJ4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IGBK7G4J","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IGBK7G4JMNHIAQJ4BBVXQ5R6JF","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09646","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3f2140084943a2445a66163cdd3e943197f4c4064b7c4d19af6c353b810d6369","abstract_canon_sha256":"a8135576c14eee229d0e5c46c76de67a0463c3a85aad6411f911095723810d07"},"schema_version":"1.0"},"canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:30.530926Z","signature_b64":"ZGoFz6ZIfpYLVBwHEQHrLiOkPrG+gomq/HknKImwRQuvLQg0QdOpq7P3D2uFxNeMjgfSNemn3eDiTfJUrMIYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","last_reissued_at":"2026-05-18T00:22:30.530175Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:30.530175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09646","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5nZ5UilCQ1Bt+CshOxEN3/OzHPxjY/N3JBrhIvcSGl7CVPClEug2jzh+Qq3GHnFxbzyTe2u/4CBwbWz8wdKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:43:53.798414Z"},"content_sha256":"9bee2ca9e9e6b6d7fe3d4cd7584e0c55db20d288509cc8ad9b140e2b84700e4e","schema_version":"1.0","event_id":"sha256:9bee2ca9e9e6b6d7fe3d4cd7584e0c55db20d288509cc8ad9b140e2b84700e4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IGBK7G4JMNHIAQJ4BBVXQ5R6JF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing over a Restricted Policy Class in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ershad Banijamali, Mohammad Ghavamzadeh, Nikos Vlassis, Yasin Abbasi-Yadkori","submitted_at":"2018-02-26T23:51:57Z","abstract_excerpt":"We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are only interested in optimizing in their convex hull. We show that this problem is NP-hard to solve exactly as well as to approximate to arbitrary accuracy. However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09646","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tsuU40WuT+MHUZwleLZd5WeFyWAi7PivGWYpJv9WZOrtLS3bJAxb8xigdaNdoscZqovsrMbCOUNL8U1ZK4tTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-01T07:43:53.798967Z"},"content_sha256":"e5369ec27bc7c8c5e53e3bb3b01602ac9308ac92b4f3a09e71ac14eed8e65692","schema_version":"1.0","event_id":"sha256:e5369ec27bc7c8c5e53e3bb3b01602ac9308ac92b4f3a09e71ac14eed8e65692"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/bundle.json","state_url":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/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":"2026-07-01T07:43:53Z","links":{"resolver":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF","bundle":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/bundle.json","state":"https://pith.science/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IGBK7G4JMNHIAQJ4BBVXQ5R6JF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IGBK7G4JMNHIAQJ4BBVXQ5R6JF","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":"a8135576c14eee229d0e5c46c76de67a0463c3a85aad6411f911095723810d07","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","title_canon_sha256":"3f2140084943a2445a66163cdd3e943197f4c4064b7c4d19af6c353b810d6369"},"schema_version":"1.0","source":{"id":"1802.09646","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09646","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09646v1","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09646","created_at":"2026-05-18T00:22:30Z"},{"alias_kind":"pith_short_12","alias_value":"IGBK7G4JMNHI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"IGBK7G4JMNHIAQJ4","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"IGBK7G4J","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:e5369ec27bc7c8c5e53e3bb3b01602ac9308ac92b4f3a09e71ac14eed8e65692","target":"graph","created_at":"2026-05-18T00:22:30Z","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":"We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem is of great interest in applications in which a number of reasonably good (or safe) policies are already known and we are only interested in optimizing in their convex hull. We show that this problem is NP-hard to solve exactly as well as to approximate to arbitrary accuracy. However, under a condition that is akin to the occupancy measures of the base policies having large overlap, we show that there exists an effic","authors_text":"Ershad Banijamali, Mohammad Ghavamzadeh, Nikos Vlassis, Yasin Abbasi-Yadkori","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","title":"Optimizing over a Restricted Policy Class in Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09646","kind":"arxiv","version":1},"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":"sha256:9bee2ca9e9e6b6d7fe3d4cd7584e0c55db20d288509cc8ad9b140e2b84700e4e","target":"record","created_at":"2026-05-18T00:22:30Z","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":"a8135576c14eee229d0e5c46c76de67a0463c3a85aad6411f911095723810d07","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T23:51:57Z","title_canon_sha256":"3f2140084943a2445a66163cdd3e943197f4c4064b7c4d19af6c353b810d6369"},"schema_version":"1.0","source":{"id":"1802.09646","kind":"arxiv","version":1}},"canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4182af9b89634e80413c086b78763e4973d8e059346207254c8242a6bdfc8c9e","first_computed_at":"2026-05-18T00:22:30.530175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:30.530175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZGoFz6ZIfpYLVBwHEQHrLiOkPrG+gomq/HknKImwRQuvLQg0QdOpq7P3D2uFxNeMjgfSNemn3eDiTfJUrMIYCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:30.530926Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09646","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bee2ca9e9e6b6d7fe3d4cd7584e0c55db20d288509cc8ad9b140e2b84700e4e","sha256:e5369ec27bc7c8c5e53e3bb3b01602ac9308ac92b4f3a09e71ac14eed8e65692"],"state_sha256":"ad83878b6437f84cbb8ad9fe7088971b07967a54c7d0000b4f0a8b2d5ecb262f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5vRCLHHPTobylrOOos1TGLh7KIV1WUxquDUv1BfWjcn3hxiMWbR3wnpdXBp+aYyuzJRCem9bsNnUobMotbUBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-01T07:43:53.802071Z","bundle_sha256":"49c3d2ed90c2c46239dc5b2462eccbacb390c080db6fe6e83ccbe1dbdc7c6cc5"}}