{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AEAV7RLWUDSKZVUNZPPLNK7YQQ","short_pith_number":"pith:AEAV7RLW","schema_version":"1.0","canonical_sha256":"01015fc576a0e4acd68dcbdeb6abf884341bca3e1848465f372402ef69c79391","source":{"kind":"arxiv","id":"2004.14990","version":5},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Augmented Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Stooke, Aravind Srinivas, Kimin Lee, Lerrel Pinto, Michael Laskin, Pieter Abbeel","submitted_at":"2020-04-30T17:35:32Z","abstract_excerpt":"Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inp"},"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":"2004.14990","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-30T17:35:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7107a7723cec0fb66f38ab48308f9a6f9610720880100eaf96ba8a7192c4026d","abstract_canon_sha256":"bcea9c442fd39672e63025556f424e351630ede2008d0829edd9fb6637db4969"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:16.149879Z","signature_b64":"FWMpMemSMzGg+eXWHJACAJZreeNoSAHC9lcyaY1HJk/GnH8ruqxN/qArCQi7RNY9kFK6xtOwC0wzDUK1APFKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01015fc576a0e4acd68dcbdeb6abf884341bca3e1848465f372402ef69c79391","last_reissued_at":"2026-07-05T01:49:16.149407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:16.149407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Augmented Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Stooke, Aravind Srinivas, Kimin Lee, Lerrel Pinto, Michael Laskin, Pieter Abbeel","submitted_at":"2020-04-30T17:35:32Z","abstract_excerpt":"Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are still lacking on two fronts: (a) data-efficiency of learning and (b) generalization to new environments. To this end, we present Reinforcement Learning with Augmented Data (RAD), a simple plug-and-play module that can enhance most RL algorithms. We perform the first extensive study of general data augmentations for RL on both pixel-based and state-based inp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14990","kind":"arxiv","version":5},"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/2004.14990/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":"2004.14990","created_at":"2026-07-05T01:49:16.149466+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14990v5","created_at":"2026-07-05T01:49:16.149466+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14990","created_at":"2026-07-05T01:49:16.149466+00:00"},{"alias_kind":"pith_short_12","alias_value":"AEAV7RLWUDSK","created_at":"2026-07-05T01:49:16.149466+00:00"},{"alias_kind":"pith_short_16","alias_value":"AEAV7RLWUDSKZVUN","created_at":"2026-07-05T01:49:16.149466+00:00"},{"alias_kind":"pith_short_8","alias_value":"AEAV7RLW","created_at":"2026-07-05T01:49:16.149466+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03800","citing_title":"Trading Human Curation for Synthetic Augmentation in RLVR","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2310.17596","citing_title":"MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2203.12601","citing_title":"R3M: A Universal Visual Representation for Robot Manipulation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2108.03298","citing_title":"What Matters in Learning from Offline Human Demonstrations for Robot Manipulation","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07401","citing_title":"Learning myopic mixed-integer nonlinear model predictive control from expert demonstrations","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ","json":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ.json","graph_json":"https://pith.science/api/pith-number/AEAV7RLWUDSKZVUNZPPLNK7YQQ/graph.json","events_json":"https://pith.science/api/pith-number/AEAV7RLWUDSKZVUNZPPLNK7YQQ/events.json","paper":"https://pith.science/paper/AEAV7RLW"},"agent_actions":{"view_html":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ","download_json":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ.json","view_paper":"https://pith.science/paper/AEAV7RLW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14990&json=true","fetch_graph":"https://pith.science/api/pith-number/AEAV7RLWUDSKZVUNZPPLNK7YQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/AEAV7RLWUDSKZVUNZPPLNK7YQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ/action/storage_attestation","attest_author":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ/action/author_attestation","sign_citation":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ/action/citation_signature","submit_replication":"https://pith.science/pith/AEAV7RLWUDSKZVUNZPPLNK7YQQ/action/replication_record"}},"created_at":"2026-07-05T01:49:16.149466+00:00","updated_at":"2026-07-05T01:49:16.149466+00:00"}