{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:P7L2KMBQ5IJUQR4WAA7V3E3TX3","short_pith_number":"pith:P7L2KMBQ","canonical_record":{"source":{"id":"1710.11424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T12:15:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c95904294135942a9b8867dd98dca35a32856cfe8a741a652bd12e55b8f8d18","abstract_canon_sha256":"42230c638bb7f5c7368e792c93cd7d8ebe5055beb24774036e22b2721df32d85"},"schema_version":"1.0"},"canonical_sha256":"7fd7a53030ea13484796003f5d9373bed17e928c9bfa10a3e409807cc2ab5b5e","source":{"kind":"arxiv","id":"1710.11424","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:P7L2KMBQ5IJUQR4WAA7V3E3TX3","target":"record","payload":{"canonical_record":{"source":{"id":"1710.11424","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2017-10-31T12:15:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c95904294135942a9b8867dd98dca35a32856cfe8a741a652bd12e55b8f8d18","abstract_canon_sha256":"42230c638bb7f5c7368e792c93cd7d8ebe5055beb24774036e22b2721df32d85"},"schema_version":"1.0"},"canonical_sha256":"7fd7a53030ea13484796003f5d9373bed17e928c9bfa10a3e409807cc2ab5b5e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:22.525375Z","signature_b64":"0ynLsUuUnNrm+CniYmO9MHy6a9mirpyoceR6qIQKZOXRV+I9n3UOIvpXHUskIIoCP4wzIlVs2seRzHxc/wutAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd7a53030ea13484796003f5d9373bed17e928c9bfa10a3e409807cc2ab5b5e","last_reissued_at":"2026-05-18T00:02:22.524824Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:22.524824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.11424","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jslicqmc2SX2YzuqV5e77bYiRgrLnduTJnWtwv+vZ6SyYPBGMUcWfer/2Lsxwof/24/QOg2iyvTWXV8FO+ARDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:53:31.641207Z"},"content_sha256":"90a2f97f2fbc546683f9bc18822e5e2918445e99569473f8c8dce808313096cc","schema_version":"1.0","event_id":"sha256:90a2f97f2fbc546683f9bc18822e5e2918445e99569473f8c8dce808313096cc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:P7L2KMBQ5IJUQR4WAA7V3E3TX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regret Minimization for Partially Observable Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Kurt Keutzer, Peter Jin, Sergey Levine","submitted_at":"2017-10-31T12:15:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11424","kind":"arxiv","version":2},"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":"2026-05-18T00:02:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrpa+F6i1sdTguPiBdf1b9BGYfDdt8X592MafOcWN0SIbWSLCzmllT8581qZpieKUSR562D2xrWXv46g93ZGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:53:31.641861Z"},"content_sha256":"3b39b0a7485cb970949e1c776fb482505892dc2e7fdf003d101f8996a0511bd4","schema_version":"1.0","event_id":"sha256:3b39b0a7485cb970949e1c776fb482505892dc2e7fdf003d101f8996a0511bd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/bundle.json","state_url":"https://pith.science/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/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":"2026-05-30T16:53:31Z","links":{"resolver":"https://pith.science/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3","bundle":"https://pith.science/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/bundle.json","state":"https://pith.science/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7L2KMBQ5IJUQR4WAA7V3E3TX3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+UnF9kJ+1997sLZfTIhq6uED4GB3fIOzof52oVVK5xS1L7fJbdSuGxVxLGtwQoKQ/vaWLIyQlUEKyP0LUoU9Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:53:31.645171Z","bundle_sha256":"099f5b9cc9e23740a230bd00bfec64a9dc908989e3b035e78ed03010df6297d2"}}