{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DOHHZGXRI5JP5N3W425CUYE2ZP","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":"8f241145f16498d1863a566831cd982d1e626741628bb059d8d5fe30b281c591","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-01T19:03:03Z","title_canon_sha256":"904b5222ca9fe4b65855f7b57a63313e977da7ce9ccb5e6d9d7be8388be968c1"},"schema_version":"1.0","source":{"id":"2202.00710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.00710","created_at":"2026-07-05T03:53:26Z"},{"alias_kind":"arxiv_version","alias_value":"2202.00710v1","created_at":"2026-07-05T03:53:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00710","created_at":"2026-07-05T03:53:26Z"},{"alias_kind":"pith_short_12","alias_value":"DOHHZGXRI5JP","created_at":"2026-07-05T03:53:26Z"},{"alias_kind":"pith_short_16","alias_value":"DOHHZGXRI5JP5N3W","created_at":"2026-07-05T03:53:26Z"},{"alias_kind":"pith_short_8","alias_value":"DOHHZGXR","created_at":"2026-07-05T03:53:26Z"}],"graph_snapshots":[{"event_id":"sha256:f3969da86426e06bb511c9fe962069ff4152b367de7b12db6b92990b158bd3b3","target":"graph","created_at":"2026-07-05T03:53:26Z","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/2202.00710/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Much of recent Deep Reinforcement Learning success is owed to the neural architecture's potential to learn and use effective internal representations of the world. While many current algorithms access a simulator to train with a large amount of data, in realistic settings, including while playing games that may be played against people, collecting experience can be quite costly. In this paper, we introduce a deep reinforcement learning architecture whose purpose is to increase sample efficiency without sacrificing performance. We design this architecture by incorporating advances achieved in r","authors_text":"Amir Ardalan Kalantari, Doina Precup, Mohammad Amini, Sarath Chandar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-01T19:03:03Z","title":"Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00710","kind":"arxiv","version":1},"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":"sha256:132632828c96d5a5a1be8c6591dcd3ce8b5ae96a324f50e28d3511dfe4559fad","target":"record","created_at":"2026-07-05T03:53:26Z","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":"8f241145f16498d1863a566831cd982d1e626741628bb059d8d5fe30b281c591","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-01T19:03:03Z","title_canon_sha256":"904b5222ca9fe4b65855f7b57a63313e977da7ce9ccb5e6d9d7be8388be968c1"},"schema_version":"1.0","source":{"id":"2202.00710","kind":"arxiv","version":1}},"canonical_sha256":"1b8e7c9af14752feb776e6ba2a609acbc76afe69dcfc9a7269f549aabaa9ff6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b8e7c9af14752feb776e6ba2a609acbc76afe69dcfc9a7269f549aabaa9ff6c","first_computed_at":"2026-07-05T03:53:26.606484Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:53:26.606484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zAVoVb259xeHB3N6BCjM8Obfv5Wp8HPl7ABKOgG2um0tNHItkmlVRxhzoP5T1zArbW3+k9TjeSD/UYmeMW0aAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:53:26.606945Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.00710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:132632828c96d5a5a1be8c6591dcd3ce8b5ae96a324f50e28d3511dfe4559fad","sha256:f3969da86426e06bb511c9fe962069ff4152b367de7b12db6b92990b158bd3b3"],"state_sha256":"da3abdfddf3f71db2ec2ede96e0c14b654fbba8787b22fc50a243ab04a70ef63"}