{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YVO5OO4VNJJZTPBJVVHZ6O4DWX","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":"1c7111924b042652cc288cae038b98881e1d75767086cf368f6fd92e04861093","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-27T16:47:54Z","title_canon_sha256":"c8da3b7fe9add904682fd0dc4511e37d56aeb05c7a8023878999f6f50de21fdc"},"schema_version":"1.0","source":{"id":"1906.11785","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11785","created_at":"2026-07-05T01:06:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11785v3","created_at":"2026-07-05T01:06:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11785","created_at":"2026-07-05T01:06:08Z"},{"alias_kind":"pith_short_12","alias_value":"YVO5OO4VNJJZ","created_at":"2026-07-05T01:06:08Z"},{"alias_kind":"pith_short_16","alias_value":"YVO5OO4VNJJZTPBJ","created_at":"2026-07-05T01:06:08Z"},{"alias_kind":"pith_short_8","alias_value":"YVO5OO4V","created_at":"2026-07-05T01:06:08Z"}],"graph_snapshots":[{"event_id":"sha256:59b13303344266736a3a8401a9b5b7780a96281d35f4595b6ebd99cfc714d9fb","target":"graph","created_at":"2026-07-05T01:06:08Z","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/1906.11785/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anirban Santara, Balaraman Ravindran, Pabitra Mitra, Rishabh Madan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-27T16:47:54Z","title":"ExTra: Transfer-guided Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11785","kind":"arxiv","version":3},"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":"sha256:8274a5ea926e79ffe1e1a5e40b4a231f565b40de30c881e389009ed5f277a54a","target":"record","created_at":"2026-07-05T01:06:08Z","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":"1c7111924b042652cc288cae038b98881e1d75767086cf368f6fd92e04861093","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-27T16:47:54Z","title_canon_sha256":"c8da3b7fe9add904682fd0dc4511e37d56aeb05c7a8023878999f6f50de21fdc"},"schema_version":"1.0","source":{"id":"1906.11785","kind":"arxiv","version":3}},"canonical_sha256":"c55dd73b956a5399bc29ad4f9f3b83b5f2700696550b3890ad69455b50260a6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c55dd73b956a5399bc29ad4f9f3b83b5f2700696550b3890ad69455b50260a6e","first_computed_at":"2026-07-05T01:06:08.027066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:06:08.027066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KZ0GHT10oLbQnS+rdDWfmmXzoZHK912Mrkm2FPuO7fZ/gzyeD/CWWYM+vC1/dt6XuatMEV49bYANXciVGrA/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:06:08.027486Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11785","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8274a5ea926e79ffe1e1a5e40b4a231f565b40de30c881e389009ed5f277a54a","sha256:59b13303344266736a3a8401a9b5b7780a96281d35f4595b6ebd99cfc714d9fb"],"state_sha256":"f728c8ae129ba6225281afd2c88ecf1286708ac4eaaab7d7f1ec76f056793c9e"}