{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:NPXYFX5JCHROY56G6YAUMNLXOK","short_pith_number":"pith:NPXYFX5J","schema_version":"1.0","canonical_sha256":"6bef82dfa911e2ec77c6f60146357772b3b45e3c03e271538a6a2afd0b8e6a90","source":{"kind":"arxiv","id":"1902.04706","version":2},"attestation_state":"computed","paper":{"title":"Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Devin Schwab, Francesco Nori, Martin Riedmiller, Michael Neunert, Murilo F. Martins, Roland Hafner, Thomas Lampe, Tim Hertweck, Tobias Springenberg","submitted_at":"2019-02-13T02:14:13Z","abstract_excerpt":"We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxiliary task policies to utilize task features that are available only at training-time. This allows for fast learning of auxiliary policies, which subsequently generate good data for training the main, vision-based control policies. This method can be seen as an extension of the Sche"},"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":"1902.04706","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-13T02:14:13Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"a848395bddfc6dbba8161b9affc932bd37e5938b45e893f1ccd2b4ef81daf7e4","abstract_canon_sha256":"79a087ab438d3f174b09800622a7a5871032401e965f6678cb80db28ecb83ace"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:40.973693Z","signature_b64":"EzHHOjZuUD4wXDx5e/xKBi96sai1IHb0irxuyd/4MtiFcy96uHKEMxHmKe6Yby82AwE+wH8R+R2d2jKVL/GBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bef82dfa911e2ec77c6f60146357772b3b45e3c03e271538a6a2afd0b8e6a90","last_reissued_at":"2026-05-17T23:53:40.973201Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:40.973201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Devin Schwab, Francesco Nori, Martin Riedmiller, Michael Neunert, Murilo F. Martins, Roland Hafner, Thomas Lampe, Tim Hertweck, Tobias Springenberg","submitted_at":"2019-02-13T02:14:13Z","abstract_excerpt":"We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxiliary task policies to utilize task features that are available only at training-time. This allows for fast learning of auxiliary policies, which subsequently generate good data for training the main, vision-based control policies. This method can be seen as an extension of the Sche"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04706","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":""},"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":"1902.04706","created_at":"2026-05-17T23:53:40.973277+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04706v2","created_at":"2026-05-17T23:53:40.973277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04706","created_at":"2026-05-17T23:53:40.973277+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPXYFX5JCHRO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPXYFX5JCHROY56G","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPXYFX5J","created_at":"2026-05-18T12:33:24.271573+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/NPXYFX5JCHROY56G6YAUMNLXOK","json":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK.json","graph_json":"https://pith.science/api/pith-number/NPXYFX5JCHROY56G6YAUMNLXOK/graph.json","events_json":"https://pith.science/api/pith-number/NPXYFX5JCHROY56G6YAUMNLXOK/events.json","paper":"https://pith.science/paper/NPXYFX5J"},"agent_actions":{"view_html":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK","download_json":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK.json","view_paper":"https://pith.science/paper/NPXYFX5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04706&json=true","fetch_graph":"https://pith.science/api/pith-number/NPXYFX5JCHROY56G6YAUMNLXOK/graph.json","fetch_events":"https://pith.science/api/pith-number/NPXYFX5JCHROY56G6YAUMNLXOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK/action/storage_attestation","attest_author":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK/action/author_attestation","sign_citation":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK/action/citation_signature","submit_replication":"https://pith.science/pith/NPXYFX5JCHROY56G6YAUMNLXOK/action/replication_record"}},"created_at":"2026-05-17T23:53:40.973277+00:00","updated_at":"2026-05-17T23:53:40.973277+00:00"}