{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RDM4Z4DZEIVHWQOTNH74Z74FRG","short_pith_number":"pith:RDM4Z4DZ","schema_version":"1.0","canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","source":{"kind":"arxiv","id":"1709.10087","version":2},"attestation_state":"computed","paper":{"title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Aravind Rajeswaran, Emanuel Todorov, Giulia Vezzani, John Schulman, Sergey Levine, Vikash Kumar","submitted_at":"2017-09-28T17:51:13Z","abstract_excerpt":"Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotic"},"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":"1709.10087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-28T17:51:13Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c443997d3b5e23b00301e2f0db94e1e167243f2ad10c5bb479592b071fa46518","abstract_canon_sha256":"23a5690f9ca56f1e359d2f682487312c79a548f6cf023d4b69cfcec318fe4230"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:24.862794Z","signature_b64":"Cc/z+9zEa8ggioba5n+hXo0XiTeLljQ/fpkPulhTy25Mg4jQYyRO1OolvEyv3T62hh+mCAVQgVIXlOuLycnHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88d9ccf079222a7b41d369ffccff858980657ca7623927e799f94128781e307a","last_reissued_at":"2026-05-18T00:12:24.862201Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:24.862201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Aravind Rajeswaran, Emanuel Todorov, Giulia Vezzani, John Schulman, Sergey Levine, Vikash Kumar","submitted_at":"2017-09-28T17:51:13Z","abstract_excerpt":"Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10087","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":""},"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":"1709.10087","created_at":"2026-05-18T00:12:24.862330+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.10087v2","created_at":"2026-05-18T00:12:24.862330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10087","created_at":"2026-05-18T00:12:24.862330+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDM4Z4DZEIVH","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDM4Z4DZEIVHWQOT","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDM4Z4DZ","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":38,"internal_anchor_count":26,"sample":[{"citing_arxiv_id":"1906.10124","citing_title":"On Multi-Agent Learning in Team Sports Games","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02050","citing_title":"Reasoning and Generalization in RL: A Tool Use Perspective","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11388","citing_title":"Learning to Solve a Rubik's Cube with a Dexterous Hand","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2407.15134","citing_title":"Proximal Policy Distillation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2512.02193","citing_title":"From monoliths to modules: Decomposing transducers for efficient world modelling","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22376","citing_title":"Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2509.26627","citing_title":"TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2511.03828","citing_title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2602.16712","citing_title":"One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18727","citing_title":"DexHoldem: Playing Texas Hold'em with Dexterous Embodied System","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19592","citing_title":"Implicit Action Chunking for Smooth Continuous Control","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2511.03828","citing_title":"From Static Constraints to Dynamic Adaptation: Sample-Level Constraint Relaxation for Offline-to-Online Reinforcement Learning","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":211,"is_internal_anchor":true},{"citing_arxiv_id":"2505.18719","citing_title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21926","citing_title":"Information Filtering via Variational Regularization for Robot Manipulation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2409.00588","citing_title":"Diffusion Policy Policy Optimization","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":270,"is_internal_anchor":true},{"citing_arxiv_id":"2203.12601","citing_title":"R3M: A Universal Visual Representation for Robot Manipulation","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2210.00030","citing_title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG","json":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG.json","graph_json":"https://pith.science/api/pith-number/RDM4Z4DZEIVHWQOTNH74Z74FRG/graph.json","events_json":"https://pith.science/api/pith-number/RDM4Z4DZEIVHWQOTNH74Z74FRG/events.json","paper":"https://pith.science/paper/RDM4Z4DZ"},"agent_actions":{"view_html":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG","download_json":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG.json","view_paper":"https://pith.science/paper/RDM4Z4DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.10087&json=true","fetch_graph":"https://pith.science/api/pith-number/RDM4Z4DZEIVHWQOTNH74Z74FRG/graph.json","fetch_events":"https://pith.science/api/pith-number/RDM4Z4DZEIVHWQOTNH74Z74FRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/action/storage_attestation","attest_author":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/action/author_attestation","sign_citation":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/action/citation_signature","submit_replication":"https://pith.science/pith/RDM4Z4DZEIVHWQOTNH74Z74FRG/action/replication_record"}},"created_at":"2026-05-18T00:12:24.862330+00:00","updated_at":"2026-05-18T00:12:24.862330+00:00"}