{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EEQBEI3LMT3V5RCIHLKQLC5KVX","short_pith_number":"pith:EEQBEI3L","canonical_record":{"source":{"id":"1703.06471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-19T17:31:13Z","cross_cats_sorted":[],"title_canon_sha256":"bb7ab7acff77419559b7b1daa9c0a391dd26eaf481dd525d629acb2ec446d8f0","abstract_canon_sha256":"f0a3a059dd8a22b79bfebc5f98097fb92d9d1723db652d281ccdba67ba05af0d"},"schema_version":"1.0"},"canonical_sha256":"212012236b64f75ec4483ad5058baaadd65da277f3b645b934f16183e662ac7d","source":{"kind":"arxiv","id":"1703.06471","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06471","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06471v1","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06471","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"EEQBEI3LMT3V","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EEQBEI3LMT3V5RCI","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EEQBEI3L","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EEQBEI3LMT3V5RCIHLKQLC5KVX","target":"record","payload":{"canonical_record":{"source":{"id":"1703.06471","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-19T17:31:13Z","cross_cats_sorted":[],"title_canon_sha256":"bb7ab7acff77419559b7b1daa9c0a391dd26eaf481dd525d629acb2ec446d8f0","abstract_canon_sha256":"f0a3a059dd8a22b79bfebc5f98097fb92d9d1723db652d281ccdba67ba05af0d"},"schema_version":"1.0"},"canonical_sha256":"212012236b64f75ec4483ad5058baaadd65da277f3b645b934f16183e662ac7d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:22.752628Z","signature_b64":"j7v3VcadxxnZrEQmN4wOwJmdflq3OY/9bPmQwItUEagaQBVAS+UCw6EHFLWAxPALCFBboA8MZ2dQKMIX/ZunBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212012236b64f75ec4483ad5058baaadd65da277f3b645b934f16183e662ac7d","last_reissued_at":"2026-05-18T00:48:22.751969Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:22.751969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.06471","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":"2026-05-18T00:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3XJTR3W0oxXY85t5ky8KX88LMAj0sIJoFwf1cVl94Ju06OR97F731M0T9Xj7GTY3ExL5ZeowUJniULPduExADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:41:30.848570Z"},"content_sha256":"b57178cad9749e11239c0daf27d336c613b2d1b48fbeea4344c0988c4e730a22","schema_version":"1.0","event_id":"sha256:b57178cad9749e11239c0daf27d336c613b2d1b48fbeea4344c0988c4e730a22"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EEQBEI3LMT3V5RCIHLKQLC5KVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Doina Precup, Peeyush Kumar","submitted_at":"2017-03-19T17:31:13Z","abstract_excerpt":"Deliberating on large or continuous state spaces have been long standing challenges in reinforcement learning. Temporal Abstraction have somewhat made this possible, but efficiently planing using temporal abstraction still remains an issue. Moreover using spatial abstractions to learn policies for various situations at once while using temporal abstraction models is an open problem. We propose here an efficient algorithm which is convergent under linear function approximation while planning using temporally abstract actions. We show how this algorithm can be used along with randomly generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06471","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":"2026-05-18T00:48:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i6J0qBF384LTE8f8SqHckvnrnAuuKaQXjz+AmJ1hU/3H6KkPlm+EP+gmRcUQRchswWZrA6Iv30vKip5PLrlpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T18:41:30.849220Z"},"content_sha256":"d7f6c75e89134ae591fb81dc97755a7a38b77c6aaa924a04a443931e93bc0ef6","schema_version":"1.0","event_id":"sha256:d7f6c75e89134ae591fb81dc97755a7a38b77c6aaa924a04a443931e93bc0ef6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/bundle.json","state_url":"https://pith.science/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/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":"2026-05-27T18:41:30Z","links":{"resolver":"https://pith.science/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX","bundle":"https://pith.science/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/bundle.json","state":"https://pith.science/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EEQBEI3LMT3V5RCIHLKQLC5KVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EEQBEI3LMT3V5RCIHLKQLC5KVX","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":"f0a3a059dd8a22b79bfebc5f98097fb92d9d1723db652d281ccdba67ba05af0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-19T17:31:13Z","title_canon_sha256":"bb7ab7acff77419559b7b1daa9c0a391dd26eaf481dd525d629acb2ec446d8f0"},"schema_version":"1.0","source":{"id":"1703.06471","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.06471","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"arxiv_version","alias_value":"1703.06471v1","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.06471","created_at":"2026-05-18T00:48:22Z"},{"alias_kind":"pith_short_12","alias_value":"EEQBEI3LMT3V","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EEQBEI3LMT3V5RCI","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EEQBEI3L","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:d7f6c75e89134ae591fb81dc97755a7a38b77c6aaa924a04a443931e93bc0ef6","target":"graph","created_at":"2026-05-18T00:48:22Z","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":"Deliberating on large or continuous state spaces have been long standing challenges in reinforcement learning. Temporal Abstraction have somewhat made this possible, but efficiently planing using temporal abstraction still remains an issue. Moreover using spatial abstractions to learn policies for various situations at once while using temporal abstraction models is an open problem. We propose here an efficient algorithm which is convergent under linear function approximation while planning using temporally abstract actions. We show how this algorithm can be used along with randomly generated ","authors_text":"Doina Precup, Peeyush Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-19T17:31:13Z","title":"Multi-Timescale, Gradient Descent, Temporal Difference Learning with Linear Options"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.06471","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:b57178cad9749e11239c0daf27d336c613b2d1b48fbeea4344c0988c4e730a22","target":"record","created_at":"2026-05-18T00:48:22Z","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":"f0a3a059dd8a22b79bfebc5f98097fb92d9d1723db652d281ccdba67ba05af0d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-19T17:31:13Z","title_canon_sha256":"bb7ab7acff77419559b7b1daa9c0a391dd26eaf481dd525d629acb2ec446d8f0"},"schema_version":"1.0","source":{"id":"1703.06471","kind":"arxiv","version":1}},"canonical_sha256":"212012236b64f75ec4483ad5058baaadd65da277f3b645b934f16183e662ac7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"212012236b64f75ec4483ad5058baaadd65da277f3b645b934f16183e662ac7d","first_computed_at":"2026-05-18T00:48:22.751969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:48:22.751969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7v3VcadxxnZrEQmN4wOwJmdflq3OY/9bPmQwItUEagaQBVAS+UCw6EHFLWAxPALCFBboA8MZ2dQKMIX/ZunBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:48:22.752628Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.06471","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b57178cad9749e11239c0daf27d336c613b2d1b48fbeea4344c0988c4e730a22","sha256:d7f6c75e89134ae591fb81dc97755a7a38b77c6aaa924a04a443931e93bc0ef6"],"state_sha256":"f0de372f597181bd08b5bdba09af36bc1cb8457575dc25595c1e14b568676cc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BAbcmxcDQ0Vgn7FJO5HrXlOSt/RcS6JfCivAMl0/tY5R4GLRVc4EMp1d8RG6FEJf7FJaNC53iMV8jX9HvKcsBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T18:41:30.852644Z","bundle_sha256":"49957f6c515bec0d508668bdd31e81ab79472cc134df40b7d59500e462103efb"}}