{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WA5QYWMJ6HRONEF54PSXPSU5JB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"89e9fa4262db98498e438396bf1385a09c0ff75806a0e045e1b4847451094d98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:28:22Z","title_canon_sha256":"747c659478d4fc4dd311965b76f06133a80d4074541432e4ce80d9ea3009f676"},"schema_version":"1.0","source":{"id":"1609.05518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05518","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05518v2","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05518","created_at":"2026-05-18T01:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"WA5QYWMJ6HRO","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WA5QYWMJ6HRONEF5","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WA5QYWMJ","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:3cf06aa71eec6f680ab510a57b2fc2db89a6ffcf79f429d2288f9904a06794e2","target":"graph","created_at":"2026-05-18T01:03:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) brings the power of deep neural networks to bear on the generic task of trial-and-error learning, and its effectiveness has been convincingly demonstrated on tasks such as Atari video games and the game of Go. However, contemporary DRL systems inherit a number of shortcomings from the current generation of deep learning techniques. For example, they require very large datasets to work effectively, entailing that they are slow to learn even when such datasets are available. Moreover, they lack the ability to reason on an abstract level, which makes it difficult","authors_text":"Kai Arulkumaran, Marta Garnelo, Murray Shanahan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:28:22Z","title":"Towards Deep Symbolic Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05518","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e62b22f68fc14f6b2d3cd37fdc4e442aa1333ac4b7cbd280f8ebd854100b23f9","target":"record","created_at":"2026-05-18T01:03:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"89e9fa4262db98498e438396bf1385a09c0ff75806a0e045e1b4847451094d98","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:28:22Z","title_canon_sha256":"747c659478d4fc4dd311965b76f06133a80d4074541432e4ce80d9ea3009f676"},"schema_version":"1.0","source":{"id":"1609.05518","kind":"arxiv","version":2}},"canonical_sha256":"b03b0c5989f1e2e690bde3e577ca9d484216a066a640205e39fd3c3127805907","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b03b0c5989f1e2e690bde3e577ca9d484216a066a640205e39fd3c3127805907","first_computed_at":"2026-05-18T01:03:32.200876Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:32.200876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uO9Es6HoWxpkihwQyNQg3FW5ySgNhV+Y9FUVWOyCS4+1QVt3lfR3N6I8UeqbO5wgBnqfGycK6C+Z/yFFwY5cCw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:32.201412Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.05518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e62b22f68fc14f6b2d3cd37fdc4e442aa1333ac4b7cbd280f8ebd854100b23f9","sha256:3cf06aa71eec6f680ab510a57b2fc2db89a6ffcf79f429d2288f9904a06794e2"],"state_sha256":"01d5f7134ebc318ba20b30d0150836314e9e262df76360eeb011bae534d72bd2"}