{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DMRLIEQTXE25BECUM3ALRDXPQI","short_pith_number":"pith:DMRLIEQT","schema_version":"1.0","canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","source":{"kind":"arxiv","id":"2303.16563","version":2},"attestation_state":"computed","paper":{"title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Feiyang Xie, Hao Dong, Haoqi Yuan, Hongcheng Wang, Penglin Cai, Zongqing Lu","submitted_at":"2023-03-29T09:45:50Z","abstract_excerpt":"We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides "},"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":"2303.16563","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-29T09:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f65e2cbdaea637b8d5ecf101ea2608af608dd8c9e0689588cd6c29222bb2ed4","abstract_canon_sha256":"994fbafd69a3131701b529afa8c612312f3d7f527ea9edb2d31ee607e3e04346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:44.195803Z","signature_b64":"8CG5e+08CWQFBFqY41g2wErBdNgWH7mqCziWoRxUxy12p0rysoo3PL0jrsgKIxY0h/HSmczXIuAOcdc+qAnEAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b22b41213b935d0905466c0b88eef820cd09f95fbeecd0931d9771d6818eedc","last_reissued_at":"2026-07-05T07:19:44.195321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:44.195321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chi Zhang, Feiyang Xie, Hao Dong, Haoqi Yuan, Hongcheng Wang, Penglin Cai, Zongqing Lu","submitted_at":"2023-03-29T09:45:50Z","abstract_excerpt":"We study building multi-task agents in open-world environments. Without human demonstrations, learning to accomplish long-horizon tasks in a large open-world environment with reinforcement learning (RL) is extremely inefficient. To tackle this challenge, we convert the multi-task learning problem into learning basic skills and planning over the skills. Using the popular open-world game Minecraft as the testbed, we propose three types of fine-grained basic skills, and use RL with intrinsic rewards to acquire skills. A novel Finding-skill that performs exploration to find diverse items provides "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.16563","kind":"arxiv","version":2},"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/2303.16563/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":"2303.16563","created_at":"2026-07-05T07:19:44.195379+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.16563v2","created_at":"2026-07-05T07:19:44.195379+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.16563","created_at":"2026-07-05T07:19:44.195379+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMRLIEQTXE25","created_at":"2026-07-05T07:19:44.195379+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMRLIEQTXE25BECU","created_at":"2026-07-05T07:19:44.195379+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMRLIEQT","created_at":"2026-07-05T07:19:44.195379+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.12173","citing_title":"SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05907","citing_title":"EvolvingAgent: Curriculum Self-evolving Agent with Continual World Model for Long-Horizon Tasks","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2305.14992","citing_title":"Reasoning with Language Model is Planning with World Model","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2602.04129","citing_title":"KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2305.17144","citing_title":"Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02544","citing_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2307.05973","citing_title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21232","citing_title":"ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18975","citing_title":"Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21232","citing_title":"ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI","json":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI.json","graph_json":"https://pith.science/api/pith-number/DMRLIEQTXE25BECUM3ALRDXPQI/graph.json","events_json":"https://pith.science/api/pith-number/DMRLIEQTXE25BECUM3ALRDXPQI/events.json","paper":"https://pith.science/paper/DMRLIEQT"},"agent_actions":{"view_html":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI","download_json":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI.json","view_paper":"https://pith.science/paper/DMRLIEQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.16563&json=true","fetch_graph":"https://pith.science/api/pith-number/DMRLIEQTXE25BECUM3ALRDXPQI/graph.json","fetch_events":"https://pith.science/api/pith-number/DMRLIEQTXE25BECUM3ALRDXPQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/action/storage_attestation","attest_author":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/action/author_attestation","sign_citation":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/action/citation_signature","submit_replication":"https://pith.science/pith/DMRLIEQTXE25BECUM3ALRDXPQI/action/replication_record"}},"created_at":"2026-07-05T07:19:44.195379+00:00","updated_at":"2026-07-05T07:19:44.195379+00:00"}