{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AUEJWP3HFPC6SQ45ZGGDOUAPR5","short_pith_number":"pith:AUEJWP3H","schema_version":"1.0","canonical_sha256":"05089b3f672bc5e9439dc98c37500f8f4edb0495a6c0e1402b93d30a2cbfa8f6","source":{"kind":"arxiv","id":"2001.06940","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Probabilistically Complete Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Ramos, Gilad Francis, Philippe Morere, Tom Blau","submitted_at":"2020-01-20T02:11:24Z","abstract_excerpt":"Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to explore in all directions until the first positive rewards are found. To mitigate this, we propose Rapidly Randomly-exploring Reinforcement Learning (R3L). We formulate exploration as a search problem and leverage widely-used planning algorithms such as Rapidly-exploring Random Tree (RRT) to find initial solutions. These solutions are used as demonstrations to"},"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":"2001.06940","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-20T02:11:24Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"d0f46539afc195cd6a68b022eb0b9e57ad9ca144f19a8f162088584a1d735b9c","abstract_canon_sha256":"eb393e0cdbbcff1648ac8ce797f780326b37cfe6841f8dc4e4c240fbec21514b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:34:26.016678Z","signature_b64":"3c+bWGBC3DekEY2CFflEttGOY7NEQlVctNjFtS0Rb6pUDbPBJPWDka8m0tBNCb8A9dxbXZrG6hCLJNe+QlkVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05089b3f672bc5e9439dc98c37500f8f4edb0495a6c0e1402b93d30a2cbfa8f6","last_reissued_at":"2026-07-05T00:34:26.016343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:34:26.016343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Probabilistically Complete Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabio Ramos, Gilad Francis, Philippe Morere, Tom Blau","submitted_at":"2020-01-20T02:11:24Z","abstract_excerpt":"Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to explore in all directions until the first positive rewards are found. To mitigate this, we propose Rapidly Randomly-exploring Reinforcement Learning (R3L). We formulate exploration as a search problem and leverage widely-used planning algorithms such as Rapidly-exploring Random Tree (RRT) to find initial solutions. These solutions are used as demonstrations to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06940","kind":"arxiv","version":1},"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/2001.06940/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":"2001.06940","created_at":"2026-07-05T00:34:26.016400+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.06940v1","created_at":"2026-07-05T00:34:26.016400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06940","created_at":"2026-07-05T00:34:26.016400+00:00"},{"alias_kind":"pith_short_12","alias_value":"AUEJWP3HFPC6","created_at":"2026-07-05T00:34:26.016400+00:00"},{"alias_kind":"pith_short_16","alias_value":"AUEJWP3HFPC6SQ45","created_at":"2026-07-05T00:34:26.016400+00:00"},{"alias_kind":"pith_short_8","alias_value":"AUEJWP3H","created_at":"2026-07-05T00:34:26.016400+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5","json":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5.json","graph_json":"https://pith.science/api/pith-number/AUEJWP3HFPC6SQ45ZGGDOUAPR5/graph.json","events_json":"https://pith.science/api/pith-number/AUEJWP3HFPC6SQ45ZGGDOUAPR5/events.json","paper":"https://pith.science/paper/AUEJWP3H"},"agent_actions":{"view_html":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5","download_json":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5.json","view_paper":"https://pith.science/paper/AUEJWP3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.06940&json=true","fetch_graph":"https://pith.science/api/pith-number/AUEJWP3HFPC6SQ45ZGGDOUAPR5/graph.json","fetch_events":"https://pith.science/api/pith-number/AUEJWP3HFPC6SQ45ZGGDOUAPR5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5/action/storage_attestation","attest_author":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5/action/author_attestation","sign_citation":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5/action/citation_signature","submit_replication":"https://pith.science/pith/AUEJWP3HFPC6SQ45ZGGDOUAPR5/action/replication_record"}},"created_at":"2026-07-05T00:34:26.016400+00:00","updated_at":"2026-07-05T00:34:26.016400+00:00"}