{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:KPRBYYTCDABKKA5N2PHRNEP2QX","short_pith_number":"pith:KPRBYYTC","schema_version":"1.0","canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","source":{"kind":"arxiv","id":"1701.02392","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning via Recurrent Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Prithwijit Guha, Santosha K. Dwivedy, Tanmay Shankar","submitted_at":"2017-01-09T23:36:05Z","abstract_excerpt":"Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. We define 3 such RCNNs, whose forward passes execute an efficient Value Iteration, propagate beliefs of state in partially observable "},"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":"1701.02392","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-01-09T23:36:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a159335a1b777f2e468122172f315ed97107fa2720319fd6e7ece69a564702e9","abstract_canon_sha256":"f82e6f197ccab0e9589fd1f504521c4c12c33c8917cbe2bb2036443b8752b989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:04.349069Z","signature_b64":"+KRWJBhFoRHVBqIhnUsifMiOPUzmm0oZ1yrsw2MSu6geJ7Rl7c/W9sP7Jb79AgE8wrG8mRaXFifXayF254R5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e21c62621802a503add3cf1691fa85d904b0db59289e7b0fef4436d29a1cf1","last_reissued_at":"2026-05-18T00:53:04.348480Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:04.348480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning via Recurrent Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Prithwijit Guha, Santosha K. Dwivedy, Tanmay Shankar","submitted_at":"2017-01-09T23:36:05Z","abstract_excerpt":"Deep Reinforcement Learning has enabled the learning of policies for complex tasks in partially observable environments, without explicitly learning the underlying model of the tasks. While such model-free methods achieve considerable performance, they often ignore the structure of task. We present a natural representation of to Reinforcement Learning (RL) problems using Recurrent Convolutional Neural Networks (RCNNs), to better exploit this inherent structure. We define 3 such RCNNs, whose forward passes execute an efficient Value Iteration, propagate beliefs of state in partially observable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.02392","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":"1701.02392","created_at":"2026-05-18T00:53:04.348568+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.02392v1","created_at":"2026-05-18T00:53:04.348568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.02392","created_at":"2026-05-18T00:53:04.348568+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPRBYYTCDABK","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPRBYYTCDABKKA5N","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPRBYYTC","created_at":"2026-05-18T12:31:24.725408+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/KPRBYYTCDABKKA5N2PHRNEP2QX","json":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX.json","graph_json":"https://pith.science/api/pith-number/KPRBYYTCDABKKA5N2PHRNEP2QX/graph.json","events_json":"https://pith.science/api/pith-number/KPRBYYTCDABKKA5N2PHRNEP2QX/events.json","paper":"https://pith.science/paper/KPRBYYTC"},"agent_actions":{"view_html":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX","download_json":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX.json","view_paper":"https://pith.science/paper/KPRBYYTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.02392&json=true","fetch_graph":"https://pith.science/api/pith-number/KPRBYYTCDABKKA5N2PHRNEP2QX/graph.json","fetch_events":"https://pith.science/api/pith-number/KPRBYYTCDABKKA5N2PHRNEP2QX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/action/storage_attestation","attest_author":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/action/author_attestation","sign_citation":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/action/citation_signature","submit_replication":"https://pith.science/pith/KPRBYYTCDABKKA5N2PHRNEP2QX/action/replication_record"}},"created_at":"2026-05-18T00:53:04.348568+00:00","updated_at":"2026-05-18T00:53:04.348568+00:00"}