{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3VR6SM4OTXSGTYSEF34AXF7EZV","short_pith_number":"pith:3VR6SM4O","schema_version":"1.0","canonical_sha256":"dd63e9338e9de469e2442ef80b97e4cd730d0f969fd0aa7476eecac3772f28cd","source":{"kind":"arxiv","id":"2407.00633","version":2},"attestation_state":"computed","paper":{"title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Pore, Diego Dall'Alba, Riccardo Muradore","submitted_at":"2024-06-30T09:15:21Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the agent's knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations (DEAR), that uses the segmentation mask of the agent as supervision to learn disentangled representations of the environment and the agent through feature separation constraints. Unlike previous "},"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":"2407.00633","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-30T09:15:21Z","cross_cats_sorted":[],"title_canon_sha256":"5af044bf9cb36a41a639167d21048b07cb8cc12a948d828e4861f5b07e825053","abstract_canon_sha256":"4eed73e744e2155e7001412dee363958dece8c042bdd2d9f40039eb302c791e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:17.243150Z","signature_b64":"IMlXP2jg2KG7Aq4O/dG4nky+shxVaH7w7RgmIfWorMfqq4MY/+4CJQVhEIvLLwv4iPFKrQywA1gxqVGItJ4EDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd63e9338e9de469e2442ef80b97e4cd730d0f969fd0aa7476eecac3772f28cd","last_reissued_at":"2026-07-05T09:24:17.242585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:17.242585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEAR: Disentangled Environment and Agent Representations for Reinforcement Learning without Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ameya Pore, Diego Dall'Alba, Riccardo Muradore","submitted_at":"2024-06-30T09:15:21Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms can learn robotic control tasks from visual observations, but they often require a large amount of data, especially when the visual scene is complex and unstructured. In this paper, we explore how the agent's knowledge of its shape can improve the sample efficiency of visual RL methods. We propose a novel method, Disentangled Environment and Agent Representations (DEAR), that uses the segmentation mask of the agent as supervision to learn disentangled representations of the environment and the agent through feature separation constraints. Unlike previous "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00633","kind":"arxiv","version":2},"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/2407.00633/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":"2407.00633","created_at":"2026-07-05T09:24:17.242658+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00633v2","created_at":"2026-07-05T09:24:17.242658+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00633","created_at":"2026-07-05T09:24:17.242658+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VR6SM4OTXSG","created_at":"2026-07-05T09:24:17.242658+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VR6SM4OTXSGTYSE","created_at":"2026-07-05T09:24:17.242658+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VR6SM4O","created_at":"2026-07-05T09:24:17.242658+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/3VR6SM4OTXSGTYSEF34AXF7EZV","json":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV.json","graph_json":"https://pith.science/api/pith-number/3VR6SM4OTXSGTYSEF34AXF7EZV/graph.json","events_json":"https://pith.science/api/pith-number/3VR6SM4OTXSGTYSEF34AXF7EZV/events.json","paper":"https://pith.science/paper/3VR6SM4O"},"agent_actions":{"view_html":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV","download_json":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV.json","view_paper":"https://pith.science/paper/3VR6SM4O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00633&json=true","fetch_graph":"https://pith.science/api/pith-number/3VR6SM4OTXSGTYSEF34AXF7EZV/graph.json","fetch_events":"https://pith.science/api/pith-number/3VR6SM4OTXSGTYSEF34AXF7EZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV/action/storage_attestation","attest_author":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV/action/author_attestation","sign_citation":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV/action/citation_signature","submit_replication":"https://pith.science/pith/3VR6SM4OTXSGTYSEF34AXF7EZV/action/replication_record"}},"created_at":"2026-07-05T09:24:17.242658+00:00","updated_at":"2026-07-05T09:24:17.242658+00:00"}