{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MA3U3PWQP6KJPHT4TIIWIFR6FV","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":"ccdbdb2ba24875007c68abc05be9ba33274d856a67d8dfbff66f07de48b42fd3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T02:58:28Z","title_canon_sha256":"79dd27a47e6c276b1d3c9ede3e039636278a86e3233583666c9106ddad07356e"},"schema_version":"1.0","source":{"id":"1905.11583","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11583","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11583v1","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11583","created_at":"2026-05-17T23:44:52Z"},{"alias_kind":"pith_short_12","alias_value":"MA3U3PWQP6KJ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"MA3U3PWQP6KJPHT4","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"MA3U3PWQ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:89ddc228b9c5194923cf9414a15290b256fb61303bc12d57f550c0ae786b0f4c","target":"graph","created_at":"2026-05-17T23:44:52Z","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"},"paper":{"abstract_excerpt":"A fundamental issue in reinforcement learning algorithms is the balance between exploration of the environment and exploitation of information already obtained by the agent. Especially, exploration has played a critical role for both efficiency and efficacy of the learning process. However, Existing works for exploration involve task-agnostic design, that is performing well in one environment, but be ill-suited to another. To the purpose of learning an effective and efficient exploration policy in an automated manner. We formalized a feasible metric for measuring the utility of exploration bas","authors_text":"Qiwei Ye, Ruihan Yang, Tie-Yan Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T02:58:28Z","title":"Learning Efficient and Effective Exploration Policies with Counterfactual Meta Policy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11583","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":"sha256:162314f746912878f31a6994e285bd969b09d9493a0a9c26ad724d9a4def1cd4","target":"record","created_at":"2026-05-17T23:44:52Z","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":"ccdbdb2ba24875007c68abc05be9ba33274d856a67d8dfbff66f07de48b42fd3","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T02:58:28Z","title_canon_sha256":"79dd27a47e6c276b1d3c9ede3e039636278a86e3233583666c9106ddad07356e"},"schema_version":"1.0","source":{"id":"1905.11583","kind":"arxiv","version":1}},"canonical_sha256":"60374dbed07f94979e7c9a1164163e2d48ed4a0a42b302bf996615da9e063884","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60374dbed07f94979e7c9a1164163e2d48ed4a0a42b302bf996615da9e063884","first_computed_at":"2026-05-17T23:44:52.943284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:52.943284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kz0mhmvVJVQ9RNaxbQeC2Gncb+DMZxB4gZtyqoIpCW7Rzyr6yHllALzzW4ZavkIIx6kuGgwj1ZGcC+Y1Vh5WCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:52.943843Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11583","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:162314f746912878f31a6994e285bd969b09d9493a0a9c26ad724d9a4def1cd4","sha256:89ddc228b9c5194923cf9414a15290b256fb61303bc12d57f550c0ae786b0f4c"],"state_sha256":"ae3eb6f7c2a484cb311b872581f061cac60a239c509e06463eb3e5fe341eff14"}