{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RGQ6EY5M6Z6BY64YMFQMCUU27M","short_pith_number":"pith:RGQ6EY5M","schema_version":"1.0","canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","source":{"kind":"arxiv","id":"1609.07088","version":1},"attestation_state":"computed","paper":{"title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Trevor Darrell","submitted_at":"2016-09-22T17:59:25Z","abstract_excerpt":"Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations. Transfer learning can mitigate"},"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":"1609.07088","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-09-22T17:59:25Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"3466a84b6703c5c2ba08fbc4aa62a7f1969f04d149cf41f0ff74158de75eaa92","abstract_canon_sha256":"bb1bf961d96b7e5f3f4760364ff09f9ef7169f9541e77da065190f2ba3fbd545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:04.489280Z","signature_b64":"n7y/3B9aIY/STz+EJhLaZ91kiNSPuRQZrbqRbCfURI0HHJIhv1o45Bk2V0vgWkuIqz7z0OnnxfCY69trpelXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89a1e263acf67c1c7b986160c1529afb3f038aa187d730a6a13d4229b5cc0eaa","last_reissued_at":"2026-05-18T01:04:04.488918Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:04.488918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Coline Devin, Pieter Abbeel, Sergey Levine, Trevor Darrell","submitted_at":"2016-09-22T17:59:25Z","abstract_excerpt":"Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep reinforcement learning to train general purpose neural network policies alleviates some of the burden of manual representation engineering by using expressive policy classes, but exacerbates the challenge of data collection, since such methods tend to be less efficient than RL with low-dimensional, hand-designed representations. Transfer learning can mitigate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.07088","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":"1609.07088","created_at":"2026-05-18T01:04:04.488973+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.07088v1","created_at":"2026-05-18T01:04:04.488973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.07088","created_at":"2026-05-18T01:04:04.488973+00:00"},{"alias_kind":"pith_short_12","alias_value":"RGQ6EY5M6Z6B","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RGQ6EY5M6Z6BY64Y","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RGQ6EY5M","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.21898","citing_title":"Flexible Multitask Learning with Factorized Diffusion Policy","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M","json":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M.json","graph_json":"https://pith.science/api/pith-number/RGQ6EY5M6Z6BY64YMFQMCUU27M/graph.json","events_json":"https://pith.science/api/pith-number/RGQ6EY5M6Z6BY64YMFQMCUU27M/events.json","paper":"https://pith.science/paper/RGQ6EY5M"},"agent_actions":{"view_html":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M","download_json":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M.json","view_paper":"https://pith.science/paper/RGQ6EY5M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.07088&json=true","fetch_graph":"https://pith.science/api/pith-number/RGQ6EY5M6Z6BY64YMFQMCUU27M/graph.json","fetch_events":"https://pith.science/api/pith-number/RGQ6EY5M6Z6BY64YMFQMCUU27M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/action/storage_attestation","attest_author":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/action/author_attestation","sign_citation":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/action/citation_signature","submit_replication":"https://pith.science/pith/RGQ6EY5M6Z6BY64YMFQMCUU27M/action/replication_record"}},"created_at":"2026-05-18T01:04:04.488973+00:00","updated_at":"2026-05-18T01:04:04.488973+00:00"}