{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NHRLFPQKHT6XYUO6LIRSWOU3MG","short_pith_number":"pith:NHRLFPQK","schema_version":"1.0","canonical_sha256":"69e2b2be0a3cfd7c51de5a232b3a9b61a8543928f8f7c6742277ce9f524044e1","source":{"kind":"arxiv","id":"2405.03113","version":1},"attestation_state":"computed","paper":{"title":"Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhinav Peri, Amy Zhang, Anthony Wang, Caleb Chuck, Carl Qi, Chang Shi, Evan Kuo, Harshit Sikchi, Kavan Mehta, Max Rudolph, Michael J. Munje, Peter Stone, Sarthak Dayal, Scott Niekum, Shuozhe Li, Siddhant Agarwal","submitted_at":"2024-05-06T02:13:08Z","abstract_excerpt":"Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot a"},"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":"2405.03113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-06T02:13:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9aa76360e5e5b27d07bb2a2cdcbd4d4685107c126bf4ec343de1d52ce0aafd7","abstract_canon_sha256":"dd9df6d05b0a40a2d1044a81d56e4f83802d296ecac9aa10180320e8efb1702f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:58.729474Z","signature_b64":"m/U0cWSK86Mk3ZYuK0z3OH30XF917t4nirHmkHuUFLlSEKfAnv+4AZHFkjYV9msylRWwjTrPYuZ/menQZV7UDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69e2b2be0a3cfd7c51de5a232b3a9b61a8543928f8f7c6742277ce9f524044e1","last_reissued_at":"2026-07-05T08:15:58.728931Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:58.728931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhinav Peri, Amy Zhang, Anthony Wang, Caleb Chuck, Carl Qi, Chang Shi, Evan Kuo, Harshit Sikchi, Kavan Mehta, Max Rudolph, Michael J. Munje, Peter Stone, Sarthak Dayal, Scott Niekum, Shuozhe Li, Siddhant Agarwal","submitted_at":"2024-05-06T02:13:08Z","abstract_excerpt":"Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of tasks, we introduce a dynamic, interactive RL testbed based on robot air hockey. By augmenting air hockey with a large family of tasks ranging from easy tasks like reaching, to challenging ones like pushing a block by hitting it with a puck, as well as goal-based and human-interactive tasks, our testbed allows a varied assessment of RL capabilities. The robot a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03113","kind":"arxiv","version":1},"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/2405.03113/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":"2405.03113","created_at":"2026-07-05T08:15:58.729013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.03113v1","created_at":"2026-07-05T08:15:58.729013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03113","created_at":"2026-07-05T08:15:58.729013+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHRLFPQKHT6X","created_at":"2026-07-05T08:15:58.729013+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHRLFPQKHT6XYUO6","created_at":"2026-07-05T08:15:58.729013+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHRLFPQK","created_at":"2026-07-05T08:15:58.729013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11525","citing_title":"Learning Object Manipulation from Scratch via Contrastive Interaction","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG","json":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG.json","graph_json":"https://pith.science/api/pith-number/NHRLFPQKHT6XYUO6LIRSWOU3MG/graph.json","events_json":"https://pith.science/api/pith-number/NHRLFPQKHT6XYUO6LIRSWOU3MG/events.json","paper":"https://pith.science/paper/NHRLFPQK"},"agent_actions":{"view_html":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG","download_json":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG.json","view_paper":"https://pith.science/paper/NHRLFPQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.03113&json=true","fetch_graph":"https://pith.science/api/pith-number/NHRLFPQKHT6XYUO6LIRSWOU3MG/graph.json","fetch_events":"https://pith.science/api/pith-number/NHRLFPQKHT6XYUO6LIRSWOU3MG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG/action/storage_attestation","attest_author":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG/action/author_attestation","sign_citation":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG/action/citation_signature","submit_replication":"https://pith.science/pith/NHRLFPQKHT6XYUO6LIRSWOU3MG/action/replication_record"}},"created_at":"2026-07-05T08:15:58.729013+00:00","updated_at":"2026-07-05T08:15:58.729013+00:00"}