{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5PTBAZZG6M6QRACO6LNCHWE6PA","short_pith_number":"pith:5PTBAZZG","schema_version":"1.0","canonical_sha256":"ebe6106726f33d08804ef2da23d89e7819ff7c9bb6f70536aef410e901a082fa","source":{"kind":"arxiv","id":"2606.18594","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhishek Naik, A. Rupam Mahmood, Colin Bellinger, Homayoon Farrahi, Seyed Alireza Azimi","submitted_at":"2026-06-17T01:45:13Z","abstract_excerpt":"In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, joint position increment, and joint velocity across two vision-based manipulation tasks: object picking and pushing. We train policies in simulation and deploy them to the real world using sim-to-real transfer. We find that action-space representation indeed significantly affects sim-to-real performance. In particular, we find that the joint velocity action space is best for the vi"},"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":"2606.18594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-17T01:45:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"429afaa7f92830a86605e9b5e9418ba947d6e2145851b33b103625fbed7860ea","abstract_canon_sha256":"fd33a9a886fc8c6de4c6e92b5b77496864b237447dded89cb98a7ccbcf8fc6d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:41.985142Z","signature_b64":"1dJ//IzR3o+P8zBmQxMoY8aIPz8LE+rAlThyct2vX95lqNt1hc0XysGthZIHPW2e8FsVz/taQh+wxR1SYGuXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebe6106726f33d08804ef2da23d89e7819ff7c9bb6f70536aef410e901a082fa","last_reissued_at":"2026-06-19T16:11:41.984747Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:41.984747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhishek Naik, A. Rupam Mahmood, Colin Bellinger, Homayoon Farrahi, Seyed Alireza Azimi","submitted_at":"2026-06-17T01:45:13Z","abstract_excerpt":"In real-world reinforcement learning (RL), the choice of action space can play a key role in shaping motion smoothness, safety, and overall task performance. In this study, we evaluate pose increment, pose velocity, joint position increment, and joint velocity across two vision-based manipulation tasks: object picking and pushing. We train policies in simulation and deploy them to the real world using sim-to-real transfer. We find that action-space representation indeed significantly affects sim-to-real performance. In particular, we find that the joint velocity action space is best for the vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18594","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/2606.18594/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":"2606.18594","created_at":"2026-06-19T16:11:41.984808+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18594v1","created_at":"2026-06-19T16:11:41.984808+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18594","created_at":"2026-06-19T16:11:41.984808+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PTBAZZG6M6Q","created_at":"2026-06-19T16:11:41.984808+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PTBAZZG6M6QRACO","created_at":"2026-06-19T16:11:41.984808+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PTBAZZG","created_at":"2026-06-19T16:11:41.984808+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA","json":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA.json","graph_json":"https://pith.science/api/pith-number/5PTBAZZG6M6QRACO6LNCHWE6PA/graph.json","events_json":"https://pith.science/api/pith-number/5PTBAZZG6M6QRACO6LNCHWE6PA/events.json","paper":"https://pith.science/paper/5PTBAZZG"},"agent_actions":{"view_html":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA","download_json":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA.json","view_paper":"https://pith.science/paper/5PTBAZZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18594&json=true","fetch_graph":"https://pith.science/api/pith-number/5PTBAZZG6M6QRACO6LNCHWE6PA/graph.json","fetch_events":"https://pith.science/api/pith-number/5PTBAZZG6M6QRACO6LNCHWE6PA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA/action/storage_attestation","attest_author":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA/action/author_attestation","sign_citation":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA/action/citation_signature","submit_replication":"https://pith.science/pith/5PTBAZZG6M6QRACO6LNCHWE6PA/action/replication_record"}},"created_at":"2026-06-19T16:11:41.984808+00:00","updated_at":"2026-06-19T16:11:41.984808+00:00"}