{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GMUUKXVAGY5JAW7X3DLMP6RRD5","short_pith_number":"pith:GMUUKXVA","schema_version":"1.0","canonical_sha256":"3329455ea0363a905bf7d8d6c7fa311f42b65a76cb462f42c2253e39bdf958a4","source":{"kind":"arxiv","id":"2107.03380","version":3},"attestation_state":"computed","paper":{"title":"RRL: Resnet as representation for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Rutav Shah, Vikash Kumar","submitted_at":"2021-07-07T17:59:07Z","abstract_excerpt":"The ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented settings warrant operations only using the robot's proprioceptive sensor such as onboard cameras, joint encoders, etc which can be challenging for policy learning owing to the high dimensionality and partial observability issues. We propose RRL: Resnet as representation for Reinforcement Learning -- a straightforward yet effective approach that can learn compl"},"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":"2107.03380","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2021-07-07T17:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"6ab3ed993bda74bc30b7364d3583adf76b3b961d2bdbbe99aeda7552baeb1c38","abstract_canon_sha256":"00baad19161e41c558cdc3f6c3f12bfab9376033fb6f610aa3e8fa820719e9ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:31:03.439638Z","signature_b64":"rny7GNRaipGVyrl2AIgTNBaC9mt5SSCjO8+ZXeGMJ/Kzq9UpieuSHuwVigR+7t8r3wF099IxieO4ul0SOqwwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3329455ea0363a905bf7d8d6c7fa311f42b65a76cb462f42c2253e39bdf958a4","last_reissued_at":"2026-07-05T03:31:03.439188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:31:03.439188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RRL: Resnet as representation for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Rutav Shah, Vikash Kumar","submitted_at":"2021-07-07T17:59:07Z","abstract_excerpt":"The ability to autonomously learn behaviors via direct interactions in uninstrumented environments can lead to generalist robots capable of enhancing productivity or providing care in unstructured settings like homes. Such uninstrumented settings warrant operations only using the robot's proprioceptive sensor such as onboard cameras, joint encoders, etc which can be challenging for policy learning owing to the high dimensionality and partial observability issues. We propose RRL: Resnet as representation for Reinforcement Learning -- a straightforward yet effective approach that can learn compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03380","kind":"arxiv","version":3},"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/2107.03380/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":"2107.03380","created_at":"2026-07-05T03:31:03.439241+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03380v3","created_at":"2026-07-05T03:31:03.439241+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03380","created_at":"2026-07-05T03:31:03.439241+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMUUKXVAGY5J","created_at":"2026-07-05T03:31:03.439241+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMUUKXVAGY5JAW7X","created_at":"2026-07-05T03:31:03.439241+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMUUKXVA","created_at":"2026-07-05T03:31:03.439241+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.02635","citing_title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2203.12601","citing_title":"R3M: A Universal Visual Representation for Robot Manipulation","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2210.00030","citing_title":"VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5","json":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5.json","graph_json":"https://pith.science/api/pith-number/GMUUKXVAGY5JAW7X3DLMP6RRD5/graph.json","events_json":"https://pith.science/api/pith-number/GMUUKXVAGY5JAW7X3DLMP6RRD5/events.json","paper":"https://pith.science/paper/GMUUKXVA"},"agent_actions":{"view_html":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5","download_json":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5.json","view_paper":"https://pith.science/paper/GMUUKXVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03380&json=true","fetch_graph":"https://pith.science/api/pith-number/GMUUKXVAGY5JAW7X3DLMP6RRD5/graph.json","fetch_events":"https://pith.science/api/pith-number/GMUUKXVAGY5JAW7X3DLMP6RRD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5/action/storage_attestation","attest_author":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5/action/author_attestation","sign_citation":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5/action/citation_signature","submit_replication":"https://pith.science/pith/GMUUKXVAGY5JAW7X3DLMP6RRD5/action/replication_record"}},"created_at":"2026-07-05T03:31:03.439241+00:00","updated_at":"2026-07-05T03:31:03.439241+00:00"}