{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GOCB52UYT7DLFSUVCUDKVBRXUK","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":"804efead5a04e37afe8a85bbd8dcef23b8a0758361dfb896465322494a469d66","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T18:59:53Z","title_canon_sha256":"cb6c48a62d32b13db62d6e7d85cc296f0ce3033609582be057d397103eea94c6"},"schema_version":"1.0","source":{"id":"2412.12098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12098","created_at":"2026-07-05T11:46:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12098v2","created_at":"2026-07-05T11:46:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12098","created_at":"2026-07-05T11:46:20Z"},{"alias_kind":"pith_short_12","alias_value":"GOCB52UYT7DL","created_at":"2026-07-05T11:46:20Z"},{"alias_kind":"pith_short_16","alias_value":"GOCB52UYT7DLFSUV","created_at":"2026-07-05T11:46:20Z"},{"alias_kind":"pith_short_8","alias_value":"GOCB52UY","created_at":"2026-07-05T11:46:20Z"}],"graph_snapshots":[{"event_id":"sha256:667e8839dbb0df565dbf48d89cb3a63a5b732b6fd1833b3edde8c9623abcf4d4","target":"graph","created_at":"2026-07-05T11:46:20Z","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/2412.12098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) algorithms aim to balance exploiting the current best strategy with exploring new options that could lead to higher rewards. Most common RL algorithms use undirected exploration, i.e., select random sequences of actions. Exploration can also be directed using intrinsic rewards, such as curiosity or model epistemic uncertainty. However, effectively balancing task and intrinsic rewards is challenging and often task-dependent. In this work, we introduce a framework, MaxInfoRL, for balancing intrinsic and extrinsic exploration. MaxInfoRL steers exploration towards infor","authors_text":"Andreas Krause, Bhavya Sukhija, Carmelo Sferrazza, Pieter Abbeel, Stelian Coros","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T18:59:53Z","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12098","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":"sha256:2750f86b7225e5342747af7eaa35911821283024466755dbbecffc55ead1e36b","target":"record","created_at":"2026-07-05T11:46:20Z","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":"804efead5a04e37afe8a85bbd8dcef23b8a0758361dfb896465322494a469d66","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-16T18:59:53Z","title_canon_sha256":"cb6c48a62d32b13db62d6e7d85cc296f0ce3033609582be057d397103eea94c6"},"schema_version":"1.0","source":{"id":"2412.12098","kind":"arxiv","version":2}},"canonical_sha256":"33841eea989fc6b2ca951506aa8637a2a1e8703e766c5dba77928c36743a7d68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33841eea989fc6b2ca951506aa8637a2a1e8703e766c5dba77928c36743a7d68","first_computed_at":"2026-07-05T11:46:20.596806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:20.596806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNvwzQ8jD3SzlJCWXG4wQ3BGQXNFLs7ZBw7LOrtjh4//9h6NPY0UUFiI8heehrwVbAo2NQUAj53KoAIrIlO5Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:20.597428Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2750f86b7225e5342747af7eaa35911821283024466755dbbecffc55ead1e36b","sha256:667e8839dbb0df565dbf48d89cb3a63a5b732b6fd1833b3edde8c9623abcf4d4"],"state_sha256":"a2eceac6bec1e748d3848b5744e4e82b1c61a22cfc9f781381d89eb0937eef30"}