{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PEGVE5IXCF5Q5M23BN5A6GW6N4","short_pith_number":"pith:PEGVE5IX","schema_version":"1.0","canonical_sha256":"790d527517117b0eb35b0b7a0f1ade6f1bb978f48a5e3ae20114b3a7bc227385","source":{"kind":"arxiv","id":"1705.07269","version":1},"attestation_state":"computed","paper":{"title":"Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aravind Suresh, Balaraman Ravindran, Rahul Ramesh, Sahil Sharma","submitted_at":"2017-05-20T07:18:40Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to have underlying compositional structure in the said action space. Such action spaces often contain actions such as go left, go up as well as go diagonally up and left (which is a composition of the former two actions). The representations of control policies in such domains have traditionally been modeled without exploiting this inherent compositional structure"},"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":"1705.07269","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-20T07:18:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23c5b23b74f9cc95bcd52ed39215627b97b2c6274b947ff7bb1a24b81c1167d2","abstract_canon_sha256":"4e378a8fdd21fcdf79f3fa8ab7f604c9e9cec4095e2514df9c5b3822058541fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:06.151372Z","signature_b64":"Gznd96r4nEYVatfNLEqQUyYfKQfj29p5q8wmRhsQCWmO2Lq2lGFFN9XddBIwqd2cNPsCbWLONThNE9vf/V8OCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"790d527517117b0eb35b0b7a0f1ade6f1bb978f48a5e3ae20114b3a7bc227385","last_reissued_at":"2026-05-18T00:44:06.150692Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:06.150692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aravind Suresh, Balaraman Ravindran, Rahul Ramesh, Sahil Sharma","submitted_at":"2017-05-20T07:18:40Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) methods have performed well in an increasing numbering of high-dimensional visual decision making domains. Among all such visual decision making problems, those with discrete action spaces often tend to have underlying compositional structure in the said action space. Such action spaces often contain actions such as go left, go up as well as go diagonally up and left (which is a composition of the former two actions). The representations of control policies in such domains have traditionally been modeled without exploiting this inherent compositional structure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07269","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":"1705.07269","created_at":"2026-05-18T00:44:06.150796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07269v1","created_at":"2026-05-18T00:44:06.150796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07269","created_at":"2026-05-18T00:44:06.150796+00:00"},{"alias_kind":"pith_short_12","alias_value":"PEGVE5IXCF5Q","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PEGVE5IXCF5Q5M23","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PEGVE5IX","created_at":"2026-05-18T12:31:37.085036+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/PEGVE5IXCF5Q5M23BN5A6GW6N4","json":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4.json","graph_json":"https://pith.science/api/pith-number/PEGVE5IXCF5Q5M23BN5A6GW6N4/graph.json","events_json":"https://pith.science/api/pith-number/PEGVE5IXCF5Q5M23BN5A6GW6N4/events.json","paper":"https://pith.science/paper/PEGVE5IX"},"agent_actions":{"view_html":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4","download_json":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4.json","view_paper":"https://pith.science/paper/PEGVE5IX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07269&json=true","fetch_graph":"https://pith.science/api/pith-number/PEGVE5IXCF5Q5M23BN5A6GW6N4/graph.json","fetch_events":"https://pith.science/api/pith-number/PEGVE5IXCF5Q5M23BN5A6GW6N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4/action/storage_attestation","attest_author":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4/action/author_attestation","sign_citation":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4/action/citation_signature","submit_replication":"https://pith.science/pith/PEGVE5IXCF5Q5M23BN5A6GW6N4/action/replication_record"}},"created_at":"2026-05-18T00:44:06.150796+00:00","updated_at":"2026-05-18T00:44:06.150796+00:00"}