{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:2JKBI4LBVTGCSFH74PRWHHVF4Z","short_pith_number":"pith:2JKBI4LB","schema_version":"1.0","canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","source":{"kind":"arxiv","id":"1507.01273","version":2},"attestation_state":"computed","paper":{"title":"Learning Deep Neural Network Policies with Continuous Memory States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Marvin Zhang, Pieter Abbeel, Sergey Levine, Zoe McCarthy","submitted_at":"2015-07-05T20:54:57Z","abstract_excerpt":"Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional, continuous systems, such as robotic manipulators. Our approach consists of augmenting the state and action space of the system with continuous-valued memory states that the policy can read from and write to. Learning general-purpose policies with this type of memory representation directly is difficult, because the policy must automatically figure out the most sali"},"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":"1507.01273","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-07-05T20:54:57Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"229cef81e139b6d9adb2356e5a00113dd7048c4e9c22fa121bcf224f3651894b","abstract_canon_sha256":"de593ff9a052ea07f3ce6e02e92d82121eb16d6057918b7b2cf25352963fedbc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:18.367591Z","signature_b64":"uRDUz/4MIjTX1zaxLJwG1MmzPDf8bkZPCZM+PwTfEH4NHjKd/J/v94ZCvekyE48x7wtuJ83/Z6yHh/rdUPPeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d254147161accc2914ffe3e3639ea5e66b5b48730dfae0fd708a18fe2b18288d","last_reissued_at":"2026-05-18T01:32:18.366052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:18.366052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Neural Network Policies with Continuous Memory States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Chelsea Finn, Marvin Zhang, Pieter Abbeel, Sergey Levine, Zoe McCarthy","submitted_at":"2015-07-05T20:54:57Z","abstract_excerpt":"Policy learning for partially observed control tasks requires policies that can remember salient information from past observations. In this paper, we present a method for learning policies with internal memory for high-dimensional, continuous systems, such as robotic manipulators. Our approach consists of augmenting the state and action space of the system with continuous-valued memory states that the policy can read from and write to. Learning general-purpose policies with this type of memory representation directly is difficult, because the policy must automatically figure out the most sali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.01273","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":"1507.01273","created_at":"2026-05-18T01:32:18.366156+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.01273v2","created_at":"2026-05-18T01:32:18.366156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.01273","created_at":"2026-05-18T01:32:18.366156+00:00"},{"alias_kind":"pith_short_12","alias_value":"2JKBI4LBVTGC","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_16","alias_value":"2JKBI4LBVTGCSFH7","created_at":"2026-05-18T12:28:59.999130+00:00"},{"alias_kind":"pith_short_8","alias_value":"2JKBI4LB","created_at":"2026-05-18T12:28:59.999130+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/2JKBI4LBVTGCSFH74PRWHHVF4Z","json":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z.json","graph_json":"https://pith.science/api/pith-number/2JKBI4LBVTGCSFH74PRWHHVF4Z/graph.json","events_json":"https://pith.science/api/pith-number/2JKBI4LBVTGCSFH74PRWHHVF4Z/events.json","paper":"https://pith.science/paper/2JKBI4LB"},"agent_actions":{"view_html":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z","download_json":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z.json","view_paper":"https://pith.science/paper/2JKBI4LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.01273&json=true","fetch_graph":"https://pith.science/api/pith-number/2JKBI4LBVTGCSFH74PRWHHVF4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/2JKBI4LBVTGCSFH74PRWHHVF4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/action/storage_attestation","attest_author":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/action/author_attestation","sign_citation":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/action/citation_signature","submit_replication":"https://pith.science/pith/2JKBI4LBVTGCSFH74PRWHHVF4Z/action/replication_record"}},"created_at":"2026-05-18T01:32:18.366156+00:00","updated_at":"2026-05-18T01:32:18.366156+00:00"}