{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XU2R5CJVLR32DEQWYLH6DXIFWF","short_pith_number":"pith:XU2R5CJV","schema_version":"1.0","canonical_sha256":"bd351e89355c77a19216c2cfe1dd05b1743899d777978e93613dc02a1edc3d96","source":{"kind":"arxiv","id":"2305.20065","version":2},"attestation_state":"computed","paper":{"title":"Latent Exploration for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"cs.RO","authors_text":"Alberto Silvio Chiappa, Alessandro Marin Vargas, Alexander Mathis, Ann Zixiang Huang","submitted_at":"2023-05-31T17:40:43Z","abstract_excerpt":"In Reinforcement Learning, agents learn policies by exploring and interacting with the environment. Due to the curse of dimensionality, learning policies that map high-dimensional sensory input to motor output is particularly challenging. During training, state of the art methods (SAC, PPO, etc.) explore the environment by perturbing the actuation with independent Gaussian noise. While this unstructured exploration has proven successful in numerous tasks, it can be suboptimal for overactuated systems. When multiple actuators, such as motors or muscles, drive behavior, uncorrelated perturbation"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.20065","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-05-31T17:40:43Z","cross_cats_sorted":["cs.AI","cs.LG","q-bio.NC"],"title_canon_sha256":"389ad13f9d3714fd65798a32410603c13a577a4ddce19fd93c1c8c12490d664d","abstract_canon_sha256":"3fec0c5098cd78d31ec024893475d05f3ef2458ae78f156e3feb15fca442ff3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:28.899927Z","signature_b64":"4oEe+SgeQL10PwqQqFTsr6IoeRDCJqJtPW5NeFqsLFlgz5LpLOjqp3ZA3haLLkfPk/jgd7ORentMQpTjLD1/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd351e89355c77a19216c2cfe1dd05b1743899d777978e93613dc02a1edc3d96","last_reissued_at":"2026-07-05T07:06:28.899439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:28.899439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Exploration for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","q-bio.NC"],"primary_cat":"cs.RO","authors_text":"Alberto Silvio Chiappa, Alessandro Marin Vargas, Alexander Mathis, Ann Zixiang Huang","submitted_at":"2023-05-31T17:40:43Z","abstract_excerpt":"In Reinforcement Learning, agents learn policies by exploring and interacting with the environment. Due to the curse of dimensionality, learning policies that map high-dimensional sensory input to motor output is particularly challenging. During training, state of the art methods (SAC, PPO, etc.) explore the environment by perturbing the actuation with independent Gaussian noise. While this unstructured exploration has proven successful in numerous tasks, it can be suboptimal for overactuated systems. When multiple actuators, such as motors or muscles, drive behavior, uncorrelated perturbation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.20065","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.20065/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.20065","created_at":"2026-07-05T07:06:28.899495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.20065v2","created_at":"2026-07-05T07:06:28.899495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.20065","created_at":"2026-07-05T07:06:28.899495+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU2R5CJVLR32","created_at":"2026-07-05T07:06:28.899495+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU2R5CJVLR32DEQW","created_at":"2026-07-05T07:06:28.899495+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU2R5CJV","created_at":"2026-07-05T07:06:28.899495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23768","citing_title":"Motion Tracking with Muscles: Predictive Control of a Parametric Musculoskeletal Canine Model","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF","json":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF.json","graph_json":"https://pith.science/api/pith-number/XU2R5CJVLR32DEQWYLH6DXIFWF/graph.json","events_json":"https://pith.science/api/pith-number/XU2R5CJVLR32DEQWYLH6DXIFWF/events.json","paper":"https://pith.science/paper/XU2R5CJV"},"agent_actions":{"view_html":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF","download_json":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF.json","view_paper":"https://pith.science/paper/XU2R5CJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.20065&json=true","fetch_graph":"https://pith.science/api/pith-number/XU2R5CJVLR32DEQWYLH6DXIFWF/graph.json","fetch_events":"https://pith.science/api/pith-number/XU2R5CJVLR32DEQWYLH6DXIFWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF/action/storage_attestation","attest_author":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF/action/author_attestation","sign_citation":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF/action/citation_signature","submit_replication":"https://pith.science/pith/XU2R5CJVLR32DEQWYLH6DXIFWF/action/replication_record"}},"created_at":"2026-07-05T07:06:28.899495+00:00","updated_at":"2026-07-05T07:06:28.899495+00:00"}