{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZPJ4YHZWSZBT2PEPDRCNLMN4BX","short_pith_number":"pith:ZPJ4YHZW","schema_version":"1.0","canonical_sha256":"cbd3cc1f3696433d3c8f1c44d5b1bc0debe9962dff3491ac580680f2fa07eb58","source":{"kind":"arxiv","id":"1905.02698","version":1},"attestation_state":"computed","paper":{"title":"Object Exchangeability in Reinforcement Learning: Extended Abstract","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dorsa Sadigh, John Mern, Mykel Kochenderfer","submitted_at":"2019-05-07T17:20:41Z","abstract_excerpt":"Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency"},"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":"1905.02698","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-07T17:20:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4c9c82400e98c2292c51d2dbef530c1d8ccd44c8e46da1bc80d292e0880e80ea","abstract_canon_sha256":"838c164391fc2813180b946f1b555f9cbd9c4c925e9898a0e4a25455e4b88524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:50.688174Z","signature_b64":"Uy1M0fFv0oZfy5avzpaKrKgnnqZohWcxhGsIKDAJuicoGmeMay7d2q9IjU2uXUB/TNazLXV0YcotlAccWQfHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbd3cc1f3696433d3c8f1c44d5b1bc0debe9962dff3491ac580680f2fa07eb58","last_reissued_at":"2026-05-17T23:46:50.687564Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:50.687564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object Exchangeability in Reinforcement Learning: Extended Abstract","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dorsa Sadigh, John Mern, Mykel Kochenderfer","submitted_at":"2019-05-07T17:20:41Z","abstract_excerpt":"Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02698","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":""},"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":"1905.02698","created_at":"2026-05-17T23:46:50.687655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02698v1","created_at":"2026-05-17T23:46:50.687655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02698","created_at":"2026-05-17T23:46:50.687655+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPJ4YHZWSZBT","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPJ4YHZWSZBT2PEP","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPJ4YHZW","created_at":"2026-05-18T12:33:33.725879+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/ZPJ4YHZWSZBT2PEPDRCNLMN4BX","json":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX.json","graph_json":"https://pith.science/api/pith-number/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/graph.json","events_json":"https://pith.science/api/pith-number/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/events.json","paper":"https://pith.science/paper/ZPJ4YHZW"},"agent_actions":{"view_html":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX","download_json":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX.json","view_paper":"https://pith.science/paper/ZPJ4YHZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02698&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/action/storage_attestation","attest_author":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/action/author_attestation","sign_citation":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/action/citation_signature","submit_replication":"https://pith.science/pith/ZPJ4YHZWSZBT2PEPDRCNLMN4BX/action/replication_record"}},"created_at":"2026-05-17T23:46:50.687655+00:00","updated_at":"2026-05-17T23:46:50.687655+00:00"}