{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CB5RMK7BOJRJTGIH5UYUVQLGNI","short_pith_number":"pith:CB5RMK7B","schema_version":"1.0","canonical_sha256":"107b162be17262999907ed314ac1666a279cdbd22a51d59d417b95a40bf9d37b","source":{"kind":"arxiv","id":"1804.08597","version":1},"attestation_state":"computed","paper":{"title":"Towards Symbolic Reinforcement Learning with Common Sense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aimore Resende Riquetti Dutra, Artur d'Avila Garcez, Eduardo Alonso","submitted_at":"2018-04-23T17:44:29Z","abstract_excerpt":"Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement "},"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":"1804.08597","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-23T17:44:29Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"2cd967a4231e8247ce335362f4dfdb814aa3a1a532db21c5d1b5567a73d80556","abstract_canon_sha256":"2327d642a2d39f6a373a9d4eaa9d772acd122d23d440fe113965b51939702647"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:47.769807Z","signature_b64":"V+ciN0bCFyP1qoAGsToVVhdXxiq37K8G8utoyWN7cvc47gnKfJWBWBX8eJ9kPbIGSgo4eImT6fdu3osBmvH7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107b162be17262999907ed314ac1666a279cdbd22a51d59d417b95a40bf9d37b","last_reissued_at":"2026-05-18T00:17:47.769204Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:47.769204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Symbolic Reinforcement Learning with Common Sense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aimore Resende Riquetti Dutra, Artur d'Avila Garcez, Eduardo Alonso","submitted_at":"2018-04-23T17:44:29Z","abstract_excerpt":"Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpretability. Deep Symbolic Reinforcement Learning (DSRL) seeks to incorporate such capacities to deep Q-networks (DQN) by learning a relevant symbolic representation prior to using Q-learning. In this paper, we propose a novel extension of DSRL, which we call Symbolic Reinforcement "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08597","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":"1804.08597","created_at":"2026-05-18T00:17:47.769285+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08597v1","created_at":"2026-05-18T00:17:47.769285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08597","created_at":"2026-05-18T00:17:47.769285+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB5RMK7BOJRJ","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB5RMK7BOJRJTGIH","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB5RMK7B","created_at":"2026-05-18T12:32:16.446611+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/CB5RMK7BOJRJTGIH5UYUVQLGNI","json":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI.json","graph_json":"https://pith.science/api/pith-number/CB5RMK7BOJRJTGIH5UYUVQLGNI/graph.json","events_json":"https://pith.science/api/pith-number/CB5RMK7BOJRJTGIH5UYUVQLGNI/events.json","paper":"https://pith.science/paper/CB5RMK7B"},"agent_actions":{"view_html":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI","download_json":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI.json","view_paper":"https://pith.science/paper/CB5RMK7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08597&json=true","fetch_graph":"https://pith.science/api/pith-number/CB5RMK7BOJRJTGIH5UYUVQLGNI/graph.json","fetch_events":"https://pith.science/api/pith-number/CB5RMK7BOJRJTGIH5UYUVQLGNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI/action/storage_attestation","attest_author":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI/action/author_attestation","sign_citation":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI/action/citation_signature","submit_replication":"https://pith.science/pith/CB5RMK7BOJRJTGIH5UYUVQLGNI/action/replication_record"}},"created_at":"2026-05-18T00:17:47.769285+00:00","updated_at":"2026-05-18T00:17:47.769285+00:00"}