{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7UO53RBHPYBQBOVR5I5KZGHS73","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":"3bf3dba89fbe0a7967cdde3b5f243602ca928b75fe082e7365aac83d26bb903e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-14T17:25:27Z","title_canon_sha256":"1d950b446e6ab31fa7c1221617c1c9d8a56d4f86c9561ef6e7d288cea0281bd5"},"schema_version":"1.0","source":{"id":"2007.07206","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.07206","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2007.07206v4","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07206","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"7UO53RBHPYBQ","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"7UO53RBHPYBQBOVR","created_at":"2026-07-05T02:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"7UO53RBH","created_at":"2026-07-05T02:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:9be2436325bb05bf1e6125099ec802b1751bf9ea3ca4ee2f421dd6fc2667b267","target":"graph","created_at":"2026-07-05T02:14:42Z","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/2007.07206/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many control tasks exhibit similar dynamics that can be modeled as having common latent structure. Hidden-Parameter Markov Decision Processes (HiP-MDPs) explicitly model this structure to improve sample efficiency in multi-task settings. However, this setting makes strong assumptions on the observability of the state that limit its application in real-world scenarios with rich observation spaces. In this work, we leverage ideas of common structure from the HiP-MDP setting, and extend it to enable robust state abstractions inspired by Block MDPs. We derive instantiations of this new framework f","authors_text":"Amy Zhang, Joelle Pineau, Khimya Khetarpal, Shagun Sodhani","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-14T17:25:27Z","title":"Learning Robust State Abstractions for Hidden-Parameter Block MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07206","kind":"arxiv","version":4},"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":"sha256:237b45cd7a43ff257f1606bdbd5cc04b9fb17b70532c1aefd4f5d52b4f7c0e37","target":"record","created_at":"2026-07-05T02:14:42Z","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":"3bf3dba89fbe0a7967cdde3b5f243602ca928b75fe082e7365aac83d26bb903e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-14T17:25:27Z","title_canon_sha256":"1d950b446e6ab31fa7c1221617c1c9d8a56d4f86c9561ef6e7d288cea0281bd5"},"schema_version":"1.0","source":{"id":"2007.07206","kind":"arxiv","version":4}},"canonical_sha256":"fd1dddc4277e0300bab1ea3aac98f2fed7803588c4dd889215febc7aca6b994f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1dddc4277e0300bab1ea3aac98f2fed7803588c4dd889215febc7aca6b994f","first_computed_at":"2026-07-05T02:14:42.409476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:42.409476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbUh8/wFVq1PIVeyB37gQOyi6ItFDFNT9rJK6vlYHQPTYrISsd4PIwZ8D8lxe+BzFm/QFPv+LEShjJ7LGHbXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:42.409953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.07206","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:237b45cd7a43ff257f1606bdbd5cc04b9fb17b70532c1aefd4f5d52b4f7c0e37","sha256:9be2436325bb05bf1e6125099ec802b1751bf9ea3ca4ee2f421dd6fc2667b267"],"state_sha256":"921334f9af702b658fbf106e34dce3322212bc23fb71b0b6071b4e94343a1d40"}