{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PLHOYOYKLZSYWEFZSVPMCB5JFY","short_pith_number":"pith:PLHOYOYK","schema_version":"1.0","canonical_sha256":"7aceec3b0a5e658b10b9955ec107a92e0596e3dc749b136b4792254ad36067f3","source":{"kind":"arxiv","id":"2406.06037","version":1},"attestation_state":"computed","paper":{"title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Donghu Kim, Dongyoon Hwang, Hojoon Lee, Jaegul Choo, Kyungmin Lee","submitted_at":"2024-06-10T06:06:38Z","abstract_excerpt":"Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations being limited to in-distribution environments and non-unified experimental setups. To address this, we introduce the Atari Pre-training Benchmark (Atari-PB), which pre-trains a ResNet-50 model on 10 million transitions from 50 Atari games and evaluates it across diverse environment distributions. Our experiments show that pre-training objectives focused on learning task-agnostic features (e.g., identifying objects and "},"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":"2406.06037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-10T06:06:38Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"fe98bad04ba91dc75ee190517a24ea9072eeda3f58017d5fded5d42391bd732d","abstract_canon_sha256":"aca69f6dd5be6c265c8a841e607ffa99147828b712f06a1f9d09c1b07680d3f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:37.006391Z","signature_b64":"XqLSIiVG2lP6zJrgxUazuchdClJZ12uiuc919tvjYGOMg5FfskwQM4JImFl9boZZZPBls9nQnQ6/W0wJzOMEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aceec3b0a5e658b10b9955ec107a92e0596e3dc749b136b4792254ad36067f3","last_reissued_at":"2026-07-05T08:29:37.005908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:37.005908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Pre-Training Objectives for Generalization in Vision-Based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Donghu Kim, Dongyoon Hwang, Hojoon Lee, Jaegul Choo, Kyungmin Lee","submitted_at":"2024-06-10T06:06:38Z","abstract_excerpt":"Recently, various pre-training methods have been introduced in vision-based Reinforcement Learning (RL). However, their generalization ability remains unclear due to evaluations being limited to in-distribution environments and non-unified experimental setups. To address this, we introduce the Atari Pre-training Benchmark (Atari-PB), which pre-trains a ResNet-50 model on 10 million transitions from 50 Atari games and evaluates it across diverse environment distributions. Our experiments show that pre-training objectives focused on learning task-agnostic features (e.g., identifying objects and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06037","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/2406.06037/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":"2406.06037","created_at":"2026-07-05T08:29:37.005963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.06037v1","created_at":"2026-07-05T08:29:37.005963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06037","created_at":"2026-07-05T08:29:37.005963+00:00"},{"alias_kind":"pith_short_12","alias_value":"PLHOYOYKLZSY","created_at":"2026-07-05T08:29:37.005963+00:00"},{"alias_kind":"pith_short_16","alias_value":"PLHOYOYKLZSYWEFZ","created_at":"2026-07-05T08:29:37.005963+00:00"},{"alias_kind":"pith_short_8","alias_value":"PLHOYOYK","created_at":"2026-07-05T08:29:37.005963+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/PLHOYOYKLZSYWEFZSVPMCB5JFY","json":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY.json","graph_json":"https://pith.science/api/pith-number/PLHOYOYKLZSYWEFZSVPMCB5JFY/graph.json","events_json":"https://pith.science/api/pith-number/PLHOYOYKLZSYWEFZSVPMCB5JFY/events.json","paper":"https://pith.science/paper/PLHOYOYK"},"agent_actions":{"view_html":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY","download_json":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY.json","view_paper":"https://pith.science/paper/PLHOYOYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.06037&json=true","fetch_graph":"https://pith.science/api/pith-number/PLHOYOYKLZSYWEFZSVPMCB5JFY/graph.json","fetch_events":"https://pith.science/api/pith-number/PLHOYOYKLZSYWEFZSVPMCB5JFY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY/action/storage_attestation","attest_author":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY/action/author_attestation","sign_citation":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY/action/citation_signature","submit_replication":"https://pith.science/pith/PLHOYOYKLZSYWEFZSVPMCB5JFY/action/replication_record"}},"created_at":"2026-07-05T08:29:37.005963+00:00","updated_at":"2026-07-05T08:29:37.005963+00:00"}