{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:P7L2KMBQ5IJUQR4WAA7V3E3TX3","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":"42230c638bb7f5c7368e792c93cd7d8ebe5055beb24774036e22b2721df32d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T12:15:38Z","title_canon_sha256":"7c95904294135942a9b8867dd98dca35a32856cfe8a741a652bd12e55b8f8d18"},"schema_version":"1.0","source":{"id":"1710.11424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11424","created_at":"2026-05-18T00:02:22Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11424v2","created_at":"2026-05-18T00:02:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11424","created_at":"2026-05-18T00:02:22Z"},{"alias_kind":"pith_short_12","alias_value":"P7L2KMBQ5IJU","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"P7L2KMBQ5IJUQR4W","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"P7L2KMBQ","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:3b39b0a7485cb970949e1c776fb482505892dc2e7fdf003d101f8996a0511bd4","target":"graph","created_at":"2026-05-18T00:02:22Z","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":"Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However, algorithms that estimate state and state-action value functions typically assume a fully observed state and must compensate for partial observations by using finite length observation histories or recurrent networks. In this work, we propose a new deep reinforcement learning algorithm based on counterfactual regret minimization that iteratively updates an approximati","authors_text":"Kurt Keutzer, Peter Jin, Sergey Levine","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T12:15:38Z","title":"Regret Minimization for Partially Observable Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11424","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":"sha256:90a2f97f2fbc546683f9bc18822e5e2918445e99569473f8c8dce808313096cc","target":"record","created_at":"2026-05-18T00:02:22Z","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":"42230c638bb7f5c7368e792c93cd7d8ebe5055beb24774036e22b2721df32d85","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T12:15:38Z","title_canon_sha256":"7c95904294135942a9b8867dd98dca35a32856cfe8a741a652bd12e55b8f8d18"},"schema_version":"1.0","source":{"id":"1710.11424","kind":"arxiv","version":2}},"canonical_sha256":"7fd7a53030ea13484796003f5d9373bed17e928c9bfa10a3e409807cc2ab5b5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd7a53030ea13484796003f5d9373bed17e928c9bfa10a3e409807cc2ab5b5e","first_computed_at":"2026-05-18T00:02:22.524824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:22.524824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0ynLsUuUnNrm+CniYmO9MHy6a9mirpyoceR6qIQKZOXRV+I9n3UOIvpXHUskIIoCP4wzIlVs2seRzHxc/wutAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:22.525375Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.11424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a2f97f2fbc546683f9bc18822e5e2918445e99569473f8c8dce808313096cc","sha256:3b39b0a7485cb970949e1c776fb482505892dc2e7fdf003d101f8996a0511bd4"],"state_sha256":"3f3ef7f7686c6c0e6a95482d3aa997587c01d1a67ed0638da00a8b498ca4cd97"}