{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3YZ3RDI5KQ256EWCVCVPJUKSN3","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":"249f78b6ebdad91c0171e49509595f1bddf1d4b44f9f84c3929fd46ad5a9557b","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T01:45:08Z","title_canon_sha256":"caea640db0961070aa1a3615654e3e89ced127bcd37b1dac20b816c7e221e9f4"},"schema_version":"1.0","source":{"id":"2412.06139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06139","created_at":"2026-07-05T09:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06139v1","created_at":"2026-07-05T09:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06139","created_at":"2026-07-05T09:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"3YZ3RDI5KQ25","created_at":"2026-07-05T09:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"3YZ3RDI5KQ256EWC","created_at":"2026-07-05T09:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"3YZ3RDI5","created_at":"2026-07-05T09:46:16Z"}],"graph_snapshots":[{"event_id":"sha256:9ccc8a93dd44865300299542ccdc0a13833ff00acd8fed110ac48c5a67dd379f","target":"graph","created_at":"2026-07-05T09:46:16Z","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/2412.06139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the bottlenecks preventing Deep Reinforcement Learning algorithms (DRL) from real-world applications is how to explore the environment and collect informative transitions efficiently. The present paper describes bounded exploration, a novel exploration method that integrates both 'soft' and intrinsic motivation exploration. Bounded exploration notably improved the Soft Actor-Critic algorithm's performance and its model-based extension's converging speed. It achieved the highest score in 6 out of 8 experiments. Bounded exploration presents an alternative method to introduce intrinsic mot","authors_text":"Bruce MacDonald, David Valencia, Henry Williams, Ting Qiao","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T01:45:08Z","title":"Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06139","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":"sha256:77a7f3b41d5a6bade076173deda0e574655c6cefc3c431a4573051d9edac81ce","target":"record","created_at":"2026-07-05T09:46:16Z","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":"249f78b6ebdad91c0171e49509595f1bddf1d4b44f9f84c3929fd46ad5a9557b","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-09T01:45:08Z","title_canon_sha256":"caea640db0961070aa1a3615654e3e89ced127bcd37b1dac20b816c7e221e9f4"},"schema_version":"1.0","source":{"id":"2412.06139","kind":"arxiv","version":1}},"canonical_sha256":"de33b88d1d5435df12c2a8aaf4d1526ed242698d7a23ab5966f32399517d0e42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de33b88d1d5435df12c2a8aaf4d1526ed242698d7a23ab5966f32399517d0e42","first_computed_at":"2026-07-05T09:46:16.031637Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:16.031637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1AaXDNQ8UgHa+T2hAVgJJDh29c7jJfjeDn545xLKwwv/h5ec1jLfKucPZz/e6ul6AyArUxU7zKCbk+/ODcG/Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:16.032051Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77a7f3b41d5a6bade076173deda0e574655c6cefc3c431a4573051d9edac81ce","sha256:9ccc8a93dd44865300299542ccdc0a13833ff00acd8fed110ac48c5a67dd379f"],"state_sha256":"61d4a6a75abdd3599a3025f3792bf09499bdd7e14925ee84ef40ea9f8886f967"}