{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JVZNAQDY2UV2OJB4D5COL7OGXJ","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":"f49530c2fae81687ecb4b69a865dc3d5b3896fba443eb2fea4847e3bb884d2b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T15:48:35Z","title_canon_sha256":"9040f941b0fa6996f186492b6baf1a23112d9edccad187ea170c58aa293c6e3a"},"schema_version":"1.0","source":{"id":"2211.15457","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.15457","created_at":"2026-07-05T05:29:55Z"},{"alias_kind":"arxiv_version","alias_value":"2211.15457v2","created_at":"2026-07-05T05:29:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15457","created_at":"2026-07-05T05:29:55Z"},{"alias_kind":"pith_short_12","alias_value":"JVZNAQDY2UV2","created_at":"2026-07-05T05:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"JVZNAQDY2UV2OJB4","created_at":"2026-07-05T05:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"JVZNAQDY","created_at":"2026-07-05T05:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:85ffa227768c9d76a1c10751d51d292cbd0b5fee5e8b0e8d05f985b6ba178fa4","target":"graph","created_at":"2026-07-05T05:29:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.15457/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta RL, contextual RL, and transfer learning, with a particular focus on zero-shot performance at test time, enabled by knowledge of the task parameters (also known as context). Our technical approach is based upon viewing each RL algorithm as a mapping from the MDP specifics to the near-optimal value function and policy and seek to approximate it with a hyperne","authors_text":"Charlotte Morissette, David Meger, Francois Robert Hogan, Gregory Dudek, Sahand Rezaei-Shoshtari","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T15:48:35Z","title":"Hypernetworks for Zero-shot Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15457","kind":"arxiv","version":2},"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:dc5bb124fcbbe7053fed889ea27c06c412695980d2030f0c21027efa70187943","target":"record","created_at":"2026-07-05T05:29:55Z","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":"f49530c2fae81687ecb4b69a865dc3d5b3896fba443eb2fea4847e3bb884d2b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-28T15:48:35Z","title_canon_sha256":"9040f941b0fa6996f186492b6baf1a23112d9edccad187ea170c58aa293c6e3a"},"schema_version":"1.0","source":{"id":"2211.15457","kind":"arxiv","version":2}},"canonical_sha256":"4d72d04078d52ba7243c1f44e5fdc6ba693de3ddfb48e4c9af402a840a64aa65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d72d04078d52ba7243c1f44e5fdc6ba693de3ddfb48e4c9af402a840a64aa65","first_computed_at":"2026-07-05T05:29:55.230337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:29:55.230337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/AAGUECQubfcUTZbJjCj9SLcndIwN5CuiVX1kg7a5FKGIzao8Ff8u071DtMfHmeLgl6gz6DSsBwJyMv0ipvDCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:29:55.230823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.15457","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc5bb124fcbbe7053fed889ea27c06c412695980d2030f0c21027efa70187943","sha256:85ffa227768c9d76a1c10751d51d292cbd0b5fee5e8b0e8d05f985b6ba178fa4"],"state_sha256":"2cbe21d4a839414dcc1284d8a80fc8ed5ab7e23d62958bd076708e028c288ce3"}