{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GGWT3ORO3RL6QNZGCE4MKY4HZH","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":"370723999cd51452e4cd163204db009eafb0da83e40f5fa0d6e9afa43ba15cce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-11-03T16:57:45Z","title_canon_sha256":"2da95eef3bf3020da05efdcfa209880a7d02c87cd57461654408b2909ef22bb6"},"schema_version":"1.0","source":{"id":"2211.01991","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01991","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01991v2","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01991","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"GGWT3ORO3RL6","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"GGWT3ORO3RL6QNZG","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"GGWT3ORO","created_at":"2026-07-05T05:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:5e2c11655d243a914ee1cd003b3251c74109907d3e0d86ff418919e0e7dbed2e","target":"graph","created_at":"2026-07-05T05:15:00Z","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/2211.01991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a method for partially observable reinforcement learning that uses a fully observable policy (which we call a state expert) during offline training to improve online performance. Based on Soft Actor-Critic (SAC), our agent balances performing actions similar to the state expert and getting high returns under partial observability. Our approach can leverage the f","authors_text":"Andrea Baisero, Christopher Amato, Dian Wang, Hai Nguyen, Robert Platt","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-11-03T16:57:45Z","title":"Leveraging Fully Observable Policies for Learning under Partial Observability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01991","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:f610e6061f3436486b8bd4e6c89b5ebc43a2b8b7a0dd18d735fe40f686954b98","target":"record","created_at":"2026-07-05T05:15:00Z","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":"370723999cd51452e4cd163204db009eafb0da83e40f5fa0d6e9afa43ba15cce","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2022-11-03T16:57:45Z","title_canon_sha256":"2da95eef3bf3020da05efdcfa209880a7d02c87cd57461654408b2909ef22bb6"},"schema_version":"1.0","source":{"id":"2211.01991","kind":"arxiv","version":2}},"canonical_sha256":"31ad3dba2edc57e837261138c56387c9cd17d3eacbb773280ecd4d3193a57ef1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31ad3dba2edc57e837261138c56387c9cd17d3eacbb773280ecd4d3193a57ef1","first_computed_at":"2026-07-05T05:15:00.866493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:00.866493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mw11Ik6lgBFRZAWzZYYnzCWc2fOlW1nZLUMMjZF4fQgs4/v1MQN6XUKyoMYZga9yHhOcPjAee4efKzhdti+wAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:00.867860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01991","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f610e6061f3436486b8bd4e6c89b5ebc43a2b8b7a0dd18d735fe40f686954b98","sha256:5e2c11655d243a914ee1cd003b3251c74109907d3e0d86ff418919e0e7dbed2e"],"state_sha256":"1ef38dc37e7ddd49b8427a5eca0bba4c175adf604b113481fb0285000a16d953"}