{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:FNU2Y4UAY3FSIP34JQ6HC5VDRZ","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":"99a3988ad395c1d4e9348001811bee393767e72f2e47d7afd6faf3a54f82b374","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-06T19:21:32Z","title_canon_sha256":"b86846479f6152f74b6c55e8eaeb300d2b967ca553a93280d826a8a095bfb5f9"},"schema_version":"1.0","source":{"id":"1606.01868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.01868","created_at":"2026-05-18T00:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"1606.01868v2","created_at":"2026-05-18T00:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.01868","created_at":"2026-05-18T00:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"FNU2Y4UAY3FS","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"FNU2Y4UAY3FSIP34","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"FNU2Y4UA","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:86dbc3356a8c7c73206aa511e7ec2ff922712a34aa0491892256737af447df3b","target":"graph","created_at":"2026-05-18T00:11:19Z","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":"We consider an agent's uncertainty about its environment and the problem of generalizing this uncertainty across observations. Specifically, we focus on the problem of exploration in non-tabular reinforcement learning. Drawing inspiration from the intrinsic motivation literature, we use density models to measure uncertainty, and propose a novel algorithm for deriving a pseudo-count from an arbitrary density model. This technique enables us to generalize count-based exploration algorithms to the non-tabular case. We apply our ideas to Atari 2600 games, providing sensible pseudo-counts from raw ","authors_text":"David Saxton, Georg Ostrovski, Marc G. Bellemare, Remi Munos, Sriram Srinivasan, Tom Schaul","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-06T19:21:32Z","title":"Unifying Count-Based Exploration and Intrinsic Motivation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.01868","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":"sha256:7efd733adc6381f9a9ac71f7ae9cb1f2bf891dcc82d9796ba6a11d7c160af326","target":"record","created_at":"2026-05-18T00:11:19Z","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":"99a3988ad395c1d4e9348001811bee393767e72f2e47d7afd6faf3a54f82b374","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-06-06T19:21:32Z","title_canon_sha256":"b86846479f6152f74b6c55e8eaeb300d2b967ca553a93280d826a8a095bfb5f9"},"schema_version":"1.0","source":{"id":"1606.01868","kind":"arxiv","version":2}},"canonical_sha256":"2b69ac7280c6cb243f7c4c3c7176a38e6b1b5698df2d51cfb9baaac53e7cce5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b69ac7280c6cb243f7c4c3c7176a38e6b1b5698df2d51cfb9baaac53e7cce5a","first_computed_at":"2026-05-18T00:11:19.285346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:11:19.285346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xZbzeIrCrkvL0KKgwwZgsPbRQzf3FA43vkKHJOwY8XNHsy/3yrx+WnGjm082bJaXM8YWDzOZp3nBcalVPOaiDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:11:19.286052Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.01868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7efd733adc6381f9a9ac71f7ae9cb1f2bf891dcc82d9796ba6a11d7c160af326","sha256:86dbc3356a8c7c73206aa511e7ec2ff922712a34aa0491892256737af447df3b"],"state_sha256":"85c511ddd5e7e3031122f2eeb076995024cac180dede086a893eb952064d2937"}