{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YVO5OO4VNJJZTPBJVVHZ6O4DWX","short_pith_number":"pith:YVO5OO4V","schema_version":"1.0","canonical_sha256":"c55dd73b956a5399bc29ad4f9f3b83b5f2700696550b3890ad69455b50260a6e","source":{"kind":"arxiv","id":"1906.11785","version":3},"attestation_state":"computed","paper":{"title":"ExTra: Transfer-guided Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anirban Santara, Balaraman Ravindran, Pabitra Mitra, Rishabh Madan","submitted_at":"2019-06-27T16:47:54Z","abstract_excerpt":"In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment. Transfer-guided Exploration (ExTra) samples actions from a Softmax distribution over these lower bounds. In this way, actions with potentially hi"},"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":"1906.11785","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-27T16:47:54Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c8da3b7fe9add904682fd0dc4511e37d56aeb05c7a8023878999f6f50de21fdc","abstract_canon_sha256":"1c7111924b042652cc288cae038b98881e1d75767086cf368f6fd92e04861093"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:08.027486Z","signature_b64":"KZ0GHT10oLbQnS+rdDWfmmXzoZHK912Mrkm2FPuO7fZ/gzyeD/CWWYM+vC1/dt6XuatMEV49bYANXciVGrA/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55dd73b956a5399bc29ad4f9f3b83b5f2700696550b3890ad69455b50260a6e","last_reissued_at":"2026-07-05T01:06:08.027066Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:08.027066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExTra: Transfer-guided Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anirban Santara, Balaraman Ravindran, Pabitra Mitra, Rishabh Madan","submitted_at":"2019-06-27T16:47:54Z","abstract_excerpt":"In this work we present a novel approach for transfer-guided exploration in reinforcement learning that is inspired by the human tendency to leverage experiences from similar encounters in the past while navigating a new task. Given an optimal policy in a related task-environment, we show that its bisimulation distance from the current task-environment gives a lower bound on the optimal advantage of state-action pairs in the current task-environment. Transfer-guided Exploration (ExTra) samples actions from a Softmax distribution over these lower bounds. In this way, actions with potentially hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11785","kind":"arxiv","version":3},"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/1906.11785/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":"1906.11785","created_at":"2026-07-05T01:06:08.027125+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.11785v3","created_at":"2026-07-05T01:06:08.027125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11785","created_at":"2026-07-05T01:06:08.027125+00:00"},{"alias_kind":"pith_short_12","alias_value":"YVO5OO4VNJJZ","created_at":"2026-07-05T01:06:08.027125+00:00"},{"alias_kind":"pith_short_16","alias_value":"YVO5OO4VNJJZTPBJ","created_at":"2026-07-05T01:06:08.027125+00:00"},{"alias_kind":"pith_short_8","alias_value":"YVO5OO4V","created_at":"2026-07-05T01:06:08.027125+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/YVO5OO4VNJJZTPBJVVHZ6O4DWX","json":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX.json","graph_json":"https://pith.science/api/pith-number/YVO5OO4VNJJZTPBJVVHZ6O4DWX/graph.json","events_json":"https://pith.science/api/pith-number/YVO5OO4VNJJZTPBJVVHZ6O4DWX/events.json","paper":"https://pith.science/paper/YVO5OO4V"},"agent_actions":{"view_html":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX","download_json":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX.json","view_paper":"https://pith.science/paper/YVO5OO4V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.11785&json=true","fetch_graph":"https://pith.science/api/pith-number/YVO5OO4VNJJZTPBJVVHZ6O4DWX/graph.json","fetch_events":"https://pith.science/api/pith-number/YVO5OO4VNJJZTPBJVVHZ6O4DWX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX/action/storage_attestation","attest_author":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX/action/author_attestation","sign_citation":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX/action/citation_signature","submit_replication":"https://pith.science/pith/YVO5OO4VNJJZTPBJVVHZ6O4DWX/action/replication_record"}},"created_at":"2026-07-05T01:06:08.027125+00:00","updated_at":"2026-07-05T01:06:08.027125+00:00"}