{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZK74M3OZ5KXSL3TUUNLPX3KKT6","short_pith_number":"pith:ZK74M3OZ","schema_version":"1.0","canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","source":{"kind":"arxiv","id":"1810.03880","version":3},"attestation_state":"computed","paper":{"title":"Continual State Representation Learning for Reinforcement Learning using Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz","submitted_at":"2018-10-09T09:42:53Z","abstract_excerpt":"We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to use Variational Auto-Encoders for state representation, and Generative Replay, i.e. the use of generated samples, to maintain past knowledge. We also provide a general and statistically sound method for automatic environment change detection. Our method provides efficient state r"},"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":"1810.03880","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-09T09:42:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"40fe0dd34bf7a35a76f579b0961d4b7deecbea050296bdab8e6e15e3950b0140","abstract_canon_sha256":"bba134b9ae428522cfe24651b310612ef7d5b8858a27d7e59bce1401b901e9fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:37.265174Z","signature_b64":"Z2aveAxN7XLpjaG/W+InGERjt4tJh4mEOKUaF6O5ZEMcub/t4mf8F0EkpFTL/oVU68ZbcoTJ43ZnckEE5x5uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cabfc66dd9eaaf25ee74a356fbed4a9f985b9a4ccbbeeaabd343b5122dfbab8a","last_reissued_at":"2026-05-17T23:58:37.264535Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:37.264535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual State Representation Learning for Reinforcement Learning using Generative Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Michael Garcia-Ortiz","submitted_at":"2018-10-09T09:42:53Z","abstract_excerpt":"We consider the problem of building a state representation model in a continual fashion. As the environment changes, the aim is to efficiently compress the sensory state's information without losing past knowledge. The learned features are then fed to a Reinforcement Learning algorithm to learn a policy. We propose to use Variational Auto-Encoders for state representation, and Generative Replay, i.e. the use of generated samples, to maintain past knowledge. We also provide a general and statistically sound method for automatic environment change detection. Our method provides efficient state r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03880","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":""},"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":"1810.03880","created_at":"2026-05-17T23:58:37.264635+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03880v3","created_at":"2026-05-17T23:58:37.264635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03880","created_at":"2026-05-17T23:58:37.264635+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZK74M3OZ5KXS","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZK74M3OZ5KXSL3TU","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZK74M3OZ","created_at":"2026-05-18T12:33:07.085635+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/ZK74M3OZ5KXSL3TUUNLPX3KKT6","json":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6.json","graph_json":"https://pith.science/api/pith-number/ZK74M3OZ5KXSL3TUUNLPX3KKT6/graph.json","events_json":"https://pith.science/api/pith-number/ZK74M3OZ5KXSL3TUUNLPX3KKT6/events.json","paper":"https://pith.science/paper/ZK74M3OZ"},"agent_actions":{"view_html":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6","download_json":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6.json","view_paper":"https://pith.science/paper/ZK74M3OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03880&json=true","fetch_graph":"https://pith.science/api/pith-number/ZK74M3OZ5KXSL3TUUNLPX3KKT6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZK74M3OZ5KXSL3TUUNLPX3KKT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/action/storage_attestation","attest_author":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/action/author_attestation","sign_citation":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/action/citation_signature","submit_replication":"https://pith.science/pith/ZK74M3OZ5KXSL3TUUNLPX3KKT6/action/replication_record"}},"created_at":"2026-05-17T23:58:37.264635+00:00","updated_at":"2026-05-17T23:58:37.264635+00:00"}