{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:O5ZOWU646LIW4EFPFJQYYPE2DE","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":"64dcd9923607b64ef5baa5df123594e88f6256ae45557ded8b66498097cf9b75","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T10:02:29Z","title_canon_sha256":"9a4dd8cb578539546c587b18e927b492bb47778520c74f8927783b02b4fa5fe6"},"schema_version":"1.0","source":{"id":"1909.02291","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02291","created_at":"2026-07-05T02:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02291v3","created_at":"2026-07-05T02:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02291","created_at":"2026-07-05T02:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"O5ZOWU646LIW","created_at":"2026-07-05T02:38:50Z"},{"alias_kind":"pith_short_16","alias_value":"O5ZOWU646LIW4EFP","created_at":"2026-07-05T02:38:50Z"},{"alias_kind":"pith_short_8","alias_value":"O5ZOWU64","created_at":"2026-07-05T02:38:50Z"}],"graph_snapshots":[{"event_id":"sha256:76e14aec3650fba5a9a6ef71875ca4daa6a0f30eef8cc7d80cea3932abf8bafc","target":"graph","created_at":"2026-07-05T02:38:50Z","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/1909.02291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning (TL) is a promising way to improve the sample efficiency of reinforcement learning. However, how to efficiently transfer knowledge across tasks with different state-action spaces is investigated at an early stage. Most previous studies only addressed the inconsistency across different state spaces by learning a common feature space, without considering that similar actions in different action spaces of related tasks share similar semantics. In this paper, we propose a method to learning action embeddings by leveraging this idea, and a framework that learns both state embeddin","authors_text":"Changjie Fan, Jianye Hao, Tianpei Yang, Yang Yu, Yingfeng Chen, Yu Chen, Zhipeng Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T10:02:29Z","title":"Learning Action-Transferable Policy with Action Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02291","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":"sha256:1fe863c7073471dc4e44baa0d5246cfd729d6db978d159f807b50f55a4c3005a","target":"record","created_at":"2026-07-05T02:38:50Z","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":"64dcd9923607b64ef5baa5df123594e88f6256ae45557ded8b66498097cf9b75","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-05T10:02:29Z","title_canon_sha256":"9a4dd8cb578539546c587b18e927b492bb47778520c74f8927783b02b4fa5fe6"},"schema_version":"1.0","source":{"id":"1909.02291","kind":"arxiv","version":3}},"canonical_sha256":"7772eb53dcf2d16e10af2a618c3c9a190bc76fe1703796c259ba15282655cd6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7772eb53dcf2d16e10af2a618c3c9a190bc76fe1703796c259ba15282655cd6a","first_computed_at":"2026-07-05T02:38:50.224590Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:38:50.224590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lN6cB4v8AuXReJ9tQuy7lQ/jBLEoQLxHKk7OKBd/SvJmqg9qSJ3u8Yjsaa/EtbQzApTS4ZY2XB2tnvSSYsqeAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:38:50.224970Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02291","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fe863c7073471dc4e44baa0d5246cfd729d6db978d159f807b50f55a4c3005a","sha256:76e14aec3650fba5a9a6ef71875ca4daa6a0f30eef8cc7d80cea3932abf8bafc"],"state_sha256":"b64d9fd23c0896b649b8895f9e4d58ea74481d572421219c624e879703c044a8"}