{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YIFOLTOHW6OAQ5A32RPPHBZSDN","short_pith_number":"pith:YIFOLTOH","schema_version":"1.0","canonical_sha256":"c20ae5cdc7b79c08741bd45ef387321b6d64f2e71e4014e29bd98a405f53a179","source":{"kind":"arxiv","id":"2011.03813","version":4},"attestation_state":"computed","paper":{"title":"MAGIC: Learning Macro-Actions for Online POMDP Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"David Hsu, Panpan Cai, Yiyuan Lee","submitted_at":"2020-11-07T17:18:45Z","abstract_excerpt":"The partially observable Markov decision process (POMDP) is a principled general framework for robot decision making under uncertainty, but POMDP planning suffers from high computational complexity, when long-term planning is required. While temporally-extended macro-actions help to cut down the effective planning horizon and significantly improve computational efficiency, how do we acquire good macro-actions? This paper proposes Macro-Action Generator-Critic (MAGIC), which performs offline learning of macro-actions optimized for online POMDP planning. Specifically, MAGIC learns a macro-action"},"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":"2011.03813","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2020-11-07T17:18:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b11ec7c7eef1090189ad01964cf5e092024a692d57c8952357cb42bb27b491b2","abstract_canon_sha256":"2a28ae2267fe7872091a81a1990a4e658d9cf11adfbcecf0159b4d90bb6addf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:15.166824Z","signature_b64":"SSbpy9yUXfjP9b2NpnbSD5OVTpzQXfjehaEzliLF6M2HhZXexPaW/1rcjTyKP1V8/FxvnZFCKOowSwO2/72wAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c20ae5cdc7b79c08741bd45ef387321b6d64f2e71e4014e29bd98a405f53a179","last_reissued_at":"2026-07-05T02:54:15.166357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:15.166357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAGIC: Learning Macro-Actions for Online POMDP Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"David Hsu, Panpan Cai, Yiyuan Lee","submitted_at":"2020-11-07T17:18:45Z","abstract_excerpt":"The partially observable Markov decision process (POMDP) is a principled general framework for robot decision making under uncertainty, but POMDP planning suffers from high computational complexity, when long-term planning is required. While temporally-extended macro-actions help to cut down the effective planning horizon and significantly improve computational efficiency, how do we acquire good macro-actions? This paper proposes Macro-Action Generator-Critic (MAGIC), which performs offline learning of macro-actions optimized for online POMDP planning. Specifically, MAGIC learns a macro-action"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03813","kind":"arxiv","version":4},"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/2011.03813/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":"2011.03813","created_at":"2026-07-05T02:54:15.166416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.03813v4","created_at":"2026-07-05T02:54:15.166416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03813","created_at":"2026-07-05T02:54:15.166416+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIFOLTOHW6OA","created_at":"2026-07-05T02:54:15.166416+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIFOLTOHW6OAQ5A3","created_at":"2026-07-05T02:54:15.166416+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIFOLTOH","created_at":"2026-07-05T02:54:15.166416+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01860","citing_title":"Optimizing Trajectory-Trees in Belief Space: An Application from Model Predictive Control to Task and Motion Planning","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN","json":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN.json","graph_json":"https://pith.science/api/pith-number/YIFOLTOHW6OAQ5A32RPPHBZSDN/graph.json","events_json":"https://pith.science/api/pith-number/YIFOLTOHW6OAQ5A32RPPHBZSDN/events.json","paper":"https://pith.science/paper/YIFOLTOH"},"agent_actions":{"view_html":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN","download_json":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN.json","view_paper":"https://pith.science/paper/YIFOLTOH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.03813&json=true","fetch_graph":"https://pith.science/api/pith-number/YIFOLTOHW6OAQ5A32RPPHBZSDN/graph.json","fetch_events":"https://pith.science/api/pith-number/YIFOLTOHW6OAQ5A32RPPHBZSDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN/action/storage_attestation","attest_author":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN/action/author_attestation","sign_citation":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN/action/citation_signature","submit_replication":"https://pith.science/pith/YIFOLTOHW6OAQ5A32RPPHBZSDN/action/replication_record"}},"created_at":"2026-07-05T02:54:15.166416+00:00","updated_at":"2026-07-05T02:54:15.166416+00:00"}