{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6DWYYCTOFFRYGVJZ43L3ZJS3N6","short_pith_number":"pith:6DWYYCTO","schema_version":"1.0","canonical_sha256":"f0ed8c0a6e2963835539e6d7bca65b6fb6ae98a8e3441e7872467538f36b1be4","source":{"kind":"arxiv","id":"1901.08651","version":3},"attestation_state":"computed","paper":{"title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonin Raffin, Ashley Hill, David Filliat, Natalia D\\'iaz-Rodr\\'iguez, Ren\\'e Traor\\'e, Timoth\\'ee Lesort","submitted_at":"2019-01-24T21:49:49Z","abstract_excerpt":"Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. T"},"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":"1901.08651","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-24T21:49:49Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"c3921558db47dc16d0ca6295224d43157f758beff7196485789df0193d44ddbb","abstract_canon_sha256":"d93e43476dc4dc0842704c96dbaa2cfaa521b323e368c8cc7b85af9161ddae7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:42.440803Z","signature_b64":"mRfXjvzWre0vagsWIgk1q//MB3T3NmsA3YSXQwLmc0kxbPUwAUkToyCHV0CU98aQmMWJYqWk0IPi3U9I4rObAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0ed8c0a6e2963835539e6d7bca65b6fb6ae98a8e3441e7872467538f36b1be4","last_reissued_at":"2026-05-17T23:42:42.440187Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:42.440187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonin Raffin, Ashley Hill, David Filliat, Natalia D\\'iaz-Rodr\\'iguez, Ren\\'e Traor\\'e, Timoth\\'ee Lesort","submitted_at":"2019-01-24T21:49:49Z","abstract_excerpt":"Scaling end-to-end reinforcement learning to control real robots from vision presents a series of challenges, in particular in terms of sample efficiency. Against end-to-end learning, state representation learning can help learn a compact, efficient and relevant representation of states that speeds up policy learning, reducing the number of samples needed, and that is easier to interpret. We evaluate several state representation learning methods on goal based robotics tasks and propose a new unsupervised model that stacks representations and combines strengths of several of these approaches. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.08651","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":"1901.08651","created_at":"2026-05-17T23:42:42.440277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.08651v3","created_at":"2026-05-17T23:42:42.440277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.08651","created_at":"2026-05-17T23:42:42.440277+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DWYYCTOFFRY","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DWYYCTOFFRYGVJZ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DWYYCTO","created_at":"2026-05-18T12:33:10.108867+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/6DWYYCTOFFRYGVJZ43L3ZJS3N6","json":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6.json","graph_json":"https://pith.science/api/pith-number/6DWYYCTOFFRYGVJZ43L3ZJS3N6/graph.json","events_json":"https://pith.science/api/pith-number/6DWYYCTOFFRYGVJZ43L3ZJS3N6/events.json","paper":"https://pith.science/paper/6DWYYCTO"},"agent_actions":{"view_html":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6","download_json":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6.json","view_paper":"https://pith.science/paper/6DWYYCTO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.08651&json=true","fetch_graph":"https://pith.science/api/pith-number/6DWYYCTOFFRYGVJZ43L3ZJS3N6/graph.json","fetch_events":"https://pith.science/api/pith-number/6DWYYCTOFFRYGVJZ43L3ZJS3N6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6/action/storage_attestation","attest_author":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6/action/author_attestation","sign_citation":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6/action/citation_signature","submit_replication":"https://pith.science/pith/6DWYYCTOFFRYGVJZ43L3ZJS3N6/action/replication_record"}},"created_at":"2026-05-17T23:42:42.440277+00:00","updated_at":"2026-05-17T23:42:42.440277+00:00"}