{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LT5UM3MCQNRZK2HA4V72PN5RQ7","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":"9db446cec5bd93bd53e400f5cee04f23e76ea2e2afcb8a4e02c02cdbde18b0f6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T01:07:12Z","title_canon_sha256":"5084a2752cc8020e8dfbf223562136058fdf710e01ea764cc38a624b58150d02"},"schema_version":"1.0","source":{"id":"1906.07865","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.07865","created_at":"2026-07-05T01:28:59Z"},{"alias_kind":"arxiv_version","alias_value":"1906.07865v4","created_at":"2026-07-05T01:28:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07865","created_at":"2026-07-05T01:28:59Z"},{"alias_kind":"pith_short_12","alias_value":"LT5UM3MCQNRZ","created_at":"2026-07-05T01:28:59Z"},{"alias_kind":"pith_short_16","alias_value":"LT5UM3MCQNRZK2HA","created_at":"2026-07-05T01:28:59Z"},{"alias_kind":"pith_short_8","alias_value":"LT5UM3MC","created_at":"2026-07-05T01:28:59Z"}],"graph_snapshots":[{"event_id":"sha256:852993f6ab37154bc74ee2218b0f80dcd1a3e0cfe1c2aebf4798f42f2d2fa802","target":"graph","created_at":"2026-07-05T01:28:59Z","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/1906.07865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and representation learning. The question we tackle in this paper is how to sculpt the stream of experience---how to adapt the learning system's behavior---to optimize the learning of a collection of value functions. A simple answer is to compute an intrinsic reward based on the statistics of each auxiliary learner, and use reinforcement learning to maximize that","authors_text":"Adam White, Cam Linke, Martha White, Nadia M. Ady, Thomas Degris","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T01:07:12Z","title":"Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07865","kind":"arxiv","version":4},"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":"sha256:919e0a022d67658d07fb31d34a4b0707708214acd2990027532e43c9f1201b74","target":"record","created_at":"2026-07-05T01:28:59Z","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":"9db446cec5bd93bd53e400f5cee04f23e76ea2e2afcb8a4e02c02cdbde18b0f6","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T01:07:12Z","title_canon_sha256":"5084a2752cc8020e8dfbf223562136058fdf710e01ea764cc38a624b58150d02"},"schema_version":"1.0","source":{"id":"1906.07865","kind":"arxiv","version":4}},"canonical_sha256":"5cfb466d8283639568e0e57fa7b7b187f794b4e59e334466c9d36881bd2414a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5cfb466d8283639568e0e57fa7b7b187f794b4e59e334466c9d36881bd2414a8","first_computed_at":"2026-07-05T01:28:59.980622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:59.980622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Fyd43gEz/dlcQFOobiHvkLONBefjSxqp/a74IVcg9Xx7YChwVTF5otGXGGkpVYJlFi2suvMjWpC7CcHUoRwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:59.981207Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.07865","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:919e0a022d67658d07fb31d34a4b0707708214acd2990027532e43c9f1201b74","sha256:852993f6ab37154bc74ee2218b0f80dcd1a3e0cfe1c2aebf4798f42f2d2fa802"],"state_sha256":"d79f75f54f1c2c1b7dcb72af46ccae5520aec9cbd9b459800cf7d72ac2e0db5d"}