{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:BKH6M6FTOZ3GLH5YX7CZQQFJ6S","short_pith_number":"pith:BKH6M6FT","schema_version":"1.0","canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","source":{"kind":"arxiv","id":"1502.02251","version":3},"attestation_state":"computed","paper":{"title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Marc Peter Deisenroth, Niklas Wahlstr\\\"om, Thomas B. Sch\\\"on","submitted_at":"2015-02-08T13:57:59Z","abstract_excerpt":"Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only. We introduce a data-efficient, model-based reinforcement learning algorithm that learns such a closed-loop policy directly from pixel information. The key ingredient is a deep dynamical model that uses deep auto-encoders to learn a low-dimensional embedding of im"},"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":"1502.02251","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-02-08T13:57:59Z","cross_cats_sorted":["cs.LG","cs.RO","cs.SY"],"title_canon_sha256":"c7b487b5e9ff08fcd8e859caa26841e9fe343ae3fad89f0b0c92cd19e7d83a90","abstract_canon_sha256":"cff366bd802d8570511f09907ecc98114e7b1da230dd1b85f03a34d15a5cb376"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:44:11.383849Z","signature_b64":"XwFj5lqeEmXxRdkrqaeXVNKgTsSwp9kI9xDqynlBewRIRZeVjWYGFdECTV1M433tpyLU9EURZZKC0e89qk0gDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a8fe678b37676659fb8bfc59840a9f49669d742298bb7d78cfe8c5bdb9f5df6","last_reissued_at":"2026-05-18T01:44:11.383236Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:44:11.383236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Pixels to Torques: Policy Learning with Deep Dynamical Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO","cs.SY"],"primary_cat":"stat.ML","authors_text":"Marc Peter Deisenroth, Niklas Wahlstr\\\"om, Thomas B. Sch\\\"on","submitted_at":"2015-02-08T13:57:59Z","abstract_excerpt":"Data-efficient learning in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. In this paper, we consider one instance of this challenge, the pixels to torques problem, where an agent must learn a closed-loop control policy from pixel information only. We introduce a data-efficient, model-based reinforcement learning algorithm that learns such a closed-loop policy directly from pixel information. The key ingredient is a deep dynamical model that uses deep auto-encoders to learn a low-dimensional embedding of im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02251","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":"1502.02251","created_at":"2026-05-18T01:44:11.383332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.02251v3","created_at":"2026-05-18T01:44:11.383332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02251","created_at":"2026-05-18T01:44:11.383332+00:00"},{"alias_kind":"pith_short_12","alias_value":"BKH6M6FTOZ3G","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BKH6M6FTOZ3GLH5Y","created_at":"2026-05-18T12:29:14.074870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BKH6M6FT","created_at":"2026-05-18T12:29:14.074870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2501.14377","citing_title":"Dream to Fly: Model-Based Reinforcement Learning for Vision-Based Drone Flight","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"1911.08265","citing_title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"1509.02971","citing_title":"Continuous control with deep reinforcement learning","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S","json":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S.json","graph_json":"https://pith.science/api/pith-number/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/graph.json","events_json":"https://pith.science/api/pith-number/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/events.json","paper":"https://pith.science/paper/BKH6M6FT"},"agent_actions":{"view_html":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S","download_json":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S.json","view_paper":"https://pith.science/paper/BKH6M6FT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.02251&json=true","fetch_graph":"https://pith.science/api/pith-number/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/graph.json","fetch_events":"https://pith.science/api/pith-number/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/action/storage_attestation","attest_author":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/action/author_attestation","sign_citation":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/action/citation_signature","submit_replication":"https://pith.science/pith/BKH6M6FTOZ3GLH5YX7CZQQFJ6S/action/replication_record"}},"created_at":"2026-05-18T01:44:11.383332+00:00","updated_at":"2026-05-18T01:44:11.383332+00:00"}