{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YFMXA7LKTAXCTZZV2VG2257QBI","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":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40"},"schema_version":"1.0","source":{"id":"1906.08189","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08189v5","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"YFMXA7LKTAXC","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"YFMXA7LKTAXCTZZV","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"YFMXA7LK","created_at":"2026-07-05T02:06:47Z"}],"graph_snapshots":[{"event_id":"sha256:ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e","target":"graph","created_at":"2026-07-05T02:06:47Z","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/1906.08189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek novel states, driving the agent to discover improved reward. However, while state-novelty exploration methods are suitable for tasks where novel observations correlate well with improved reward, they may not explore more efficiently than epsilon-greedy approaches in environments where the two are not well-correlated. In this paper, we distinguish between explo","authors_text":"Anthony Bisulco, Ben Eisner, Daniel Lee, Daniel Yang, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title":"Reward Prediction Error as an Exploration Objective in Deep RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08189","kind":"arxiv","version":5},"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":"sha256:6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893","target":"record","created_at":"2026-07-05T02:06:47Z","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":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40"},"schema_version":"1.0","source":{"id":"1906.08189","kind":"arxiv","version":5}},"canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","first_computed_at":"2026-07-05T02:06:47.513700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:06:47.513700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f+RJ6JvV9yik+zSvxAxnO1QLhX6FFUnEQRKQthJ2RFOZrZ3sJENgIQS+kQgyPFXhHf4rM8qWn5sABaa1z4AZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:06:47.514153Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08189","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893","sha256:ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e"],"state_sha256":"281209041061cf802fe11f7215d0daf80caeb8f180a70f583b83283968f60374"}