{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ELMWG3LZBRNYVI2DENWYW3NRWU","short_pith_number":"pith:ELMWG3LZ","schema_version":"1.0","canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","source":{"kind":"arxiv","id":"1703.00727","version":1},"attestation_state":"computed","paper":{"title":"Deep Predictive Policy Training using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, M\\r{a}rten Bj\\\"orkman","submitted_at":"2017-03-02T11:29:57Z","abstract_excerpt":"Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The percep"},"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":"1703.00727","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2017-03-02T11:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"459038ceb0b5078be8301e6ecfafc7ab115a665e524e147cd559848c2f4e7801","abstract_canon_sha256":"6fa5cfb66a2d1b6c167de8a5083d749528507c5863ec4fea3b1c46c44b1a35e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:40.947581Z","signature_b64":"oB7gZETZWJ3ym+1a2IGLaDl7xKGsKpYrMZ6t1OxAuj42XCUxB92zp1KdgwuONyfWmiTJnKfJMLo7NawHiFN/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22d9636d790c5b8aa343236d8b6db1b52616b7cff8b7bcb42f1daebc75498936","last_reissued_at":"2026-05-18T00:49:40.946890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:40.946890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Predictive Policy Training using Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Ali Ghadirzadeh, Atsuto Maki, Danica Kragic, M\\r{a}rten Bj\\\"orkman","submitted_at":"2017-03-02T11:29:57Z","abstract_excerpt":"Skilled robot task learning is best implemented by predictive action policies due to the inherent latency of sensorimotor processes. However, training such predictive policies is challenging as it involves finding a trajectory of motor activations for the full duration of the action. We propose a data-efficient deep predictive policy training (DPPT) framework with a deep neural network policy architecture which maps an image observation to a sequence of motor activations. The architecture consists of three sub-networks referred to as the perception, policy and behavior super-layers. The percep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00727","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":"1703.00727","created_at":"2026-05-18T00:49:40.946990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.00727v1","created_at":"2026-05-18T00:49:40.946990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00727","created_at":"2026-05-18T00:49:40.946990+00:00"},{"alias_kind":"pith_short_12","alias_value":"ELMWG3LZBRNY","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ELMWG3LZBRNYVI2D","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ELMWG3LZ","created_at":"2026-05-18T12:31:12.930513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.01713","citing_title":"FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU","json":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU.json","graph_json":"https://pith.science/api/pith-number/ELMWG3LZBRNYVI2DENWYW3NRWU/graph.json","events_json":"https://pith.science/api/pith-number/ELMWG3LZBRNYVI2DENWYW3NRWU/events.json","paper":"https://pith.science/paper/ELMWG3LZ"},"agent_actions":{"view_html":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU","download_json":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU.json","view_paper":"https://pith.science/paper/ELMWG3LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.00727&json=true","fetch_graph":"https://pith.science/api/pith-number/ELMWG3LZBRNYVI2DENWYW3NRWU/graph.json","fetch_events":"https://pith.science/api/pith-number/ELMWG3LZBRNYVI2DENWYW3NRWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/action/storage_attestation","attest_author":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/action/author_attestation","sign_citation":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/action/citation_signature","submit_replication":"https://pith.science/pith/ELMWG3LZBRNYVI2DENWYW3NRWU/action/replication_record"}},"created_at":"2026-05-18T00:49:40.946990+00:00","updated_at":"2026-05-18T00:49:40.946990+00:00"}