{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:N4N73LUQCOX43F5HPAQIVVW4YT","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":"1b7f86fb7e7c8d63a6cb1e8354f335784917c3cc926545bbfbd966ec611fcc24","cross_cats_sorted":["cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-12-07T09:42:21Z","title_canon_sha256":"a613ac62d0a6f368ef280fc180884da191b4c7c37c51cbc167adee0a58c9e6f9"},"schema_version":"1.0","source":{"id":"2212.03540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.03540","created_at":"2026-07-05T06:34:03Z"},{"alias_kind":"arxiv_version","alias_value":"2212.03540v2","created_at":"2026-07-05T06:34:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03540","created_at":"2026-07-05T06:34:03Z"},{"alias_kind":"pith_short_12","alias_value":"N4N73LUQCOX4","created_at":"2026-07-05T06:34:03Z"},{"alias_kind":"pith_short_16","alias_value":"N4N73LUQCOX43F5H","created_at":"2026-07-05T06:34:03Z"},{"alias_kind":"pith_short_8","alias_value":"N4N73LUQ","created_at":"2026-07-05T06:34:03Z"}],"graph_snapshots":[{"event_id":"sha256:0f038e1a711a92743324ff21ab2aece644f37937aa046eda4854a6fb8f78c795","target":"graph","created_at":"2026-07-05T06:34:03Z","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/2212.03540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Formulating expert policies as macro actions promises to alleviate the long-horizon issue via structured exploration and efficient credit assignment. However, traditional option-based multi-policy transfer methods suffer from inefficient exploration of macro action's length and insufficient exploitation of useful long-duration macro actions. In this paper, a novel algorithm named EASpace (Enhanced Action Space) is proposed, which formulates macro actions in an alternative form to accelerate the learning process using multiple available sub-optimal expert policies. Specifically, EASpace formula","authors_text":"Bo Zhu, Qingrui Zhang, Tianjiang Hu, Xiaohan Wang, Zheng Zhang","cross_cats":["cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-12-07T09:42:21Z","title":"EASpace: Enhanced Action Space for Policy Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03540","kind":"arxiv","version":2},"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":"sha256:90823b322825c0fcf1bcfffe292f8a214ea5bddf897d637511c335651e22b694","target":"record","created_at":"2026-07-05T06:34:03Z","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":"1b7f86fb7e7c8d63a6cb1e8354f335784917c3cc926545bbfbd966ec611fcc24","cross_cats_sorted":["cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2022-12-07T09:42:21Z","title_canon_sha256":"a613ac62d0a6f368ef280fc180884da191b4c7c37c51cbc167adee0a58c9e6f9"},"schema_version":"1.0","source":{"id":"2212.03540","kind":"arxiv","version":2}},"canonical_sha256":"6f1bfdae9013afcd97a778208ad6dcc4d967f5ad056ca17f8e94da9719edb9e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f1bfdae9013afcd97a778208ad6dcc4d967f5ad056ca17f8e94da9719edb9e8","first_computed_at":"2026-07-05T06:34:03.407170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:03.407170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jOOXJ6AKLdZ9iBJDPSRdIYfbvjNV8DyMSZGl2wtNt6QOY76q8dCTmLM01ta0kMRNApUe9TEJgjSmcK8K8fXYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:03.407672Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.03540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90823b322825c0fcf1bcfffe292f8a214ea5bddf897d637511c335651e22b694","sha256:0f038e1a711a92743324ff21ab2aece644f37937aa046eda4854a6fb8f78c795"],"state_sha256":"5e6bf616c27fcc382e241aa6df2d3e8048591fe6fb2bcde40c9a13a69c04a3f4"}