{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:O6EHJPL3S6EPQJ2C5Q52CM44CP","short_pith_number":"pith:O6EHJPL3","schema_version":"1.0","canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","source":{"kind":"arxiv","id":"1705.07615","version":1},"attestation_state":"computed","paper":{"title":"AIXIjs: A Software Demo for General Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Aslanides","submitted_at":"2017-05-22T08:56:54Z","abstract_excerpt":"Reinforcement learning is a general and powerful framework with which to study and implement artificial intelligence. Recent advances in deep learning have enabled RL algorithms to achieve impressive performance in restricted domains such as playing Atari video games (Mnih et al., 2015) and, recently, the board game Go (Silver et al., 2016). However, we are still far from constructing a generally intelligent agent. Many of the obstacles and open questions are conceptual: What does it mean to be intelligent? How does one explore and learn optimally in general, unknown environments? What, in fac"},"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":"1705.07615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2017-05-22T08:56:54Z","cross_cats_sorted":[],"title_canon_sha256":"c1ea65f72f70fb193351d3c8421c4b5078e5748444c1937aa1471896c62aa664","abstract_canon_sha256":"2854fe485dbba834325e2de2a789d1f955ca74c770c797e218b6974bb52f5e93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:05.039407Z","signature_b64":"QcCJ3FC9eK7MvoESfGWpqU1DIsKru4+Y/RfBn8s9InEekODZfPM3iwfTJULgcOqxcZJLrbE4+vrY8q9sQk6WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"778874bd7b9788f82742ec3ba1339c13d71e5c9c18a6ab87b01a2b580f72e56b","last_reissued_at":"2026-05-18T00:44:05.038850Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:05.038850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIXIjs: A Software Demo for General Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"John Aslanides","submitted_at":"2017-05-22T08:56:54Z","abstract_excerpt":"Reinforcement learning is a general and powerful framework with which to study and implement artificial intelligence. Recent advances in deep learning have enabled RL algorithms to achieve impressive performance in restricted domains such as playing Atari video games (Mnih et al., 2015) and, recently, the board game Go (Silver et al., 2016). However, we are still far from constructing a generally intelligent agent. Many of the obstacles and open questions are conceptual: What does it mean to be intelligent? How does one explore and learn optimally in general, unknown environments? What, in fac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07615","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":"1705.07615","created_at":"2026-05-18T00:44:05.038940+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07615v1","created_at":"2026-05-18T00:44:05.038940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07615","created_at":"2026-05-18T00:44:05.038940+00:00"},{"alias_kind":"pith_short_12","alias_value":"O6EHJPL3S6EP","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_16","alias_value":"O6EHJPL3S6EPQJ2C","created_at":"2026-05-18T12:31:34.259226+00:00"},{"alias_kind":"pith_short_8","alias_value":"O6EHJPL3","created_at":"2026-05-18T12:31:34.259226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09136","citing_title":"Categorizing Wireheading in Partially Embedded Agents","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP","json":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP.json","graph_json":"https://pith.science/api/pith-number/O6EHJPL3S6EPQJ2C5Q52CM44CP/graph.json","events_json":"https://pith.science/api/pith-number/O6EHJPL3S6EPQJ2C5Q52CM44CP/events.json","paper":"https://pith.science/paper/O6EHJPL3"},"agent_actions":{"view_html":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP","download_json":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP.json","view_paper":"https://pith.science/paper/O6EHJPL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07615&json=true","fetch_graph":"https://pith.science/api/pith-number/O6EHJPL3S6EPQJ2C5Q52CM44CP/graph.json","fetch_events":"https://pith.science/api/pith-number/O6EHJPL3S6EPQJ2C5Q52CM44CP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/action/storage_attestation","attest_author":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/action/author_attestation","sign_citation":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/action/citation_signature","submit_replication":"https://pith.science/pith/O6EHJPL3S6EPQJ2C5Q52CM44CP/action/replication_record"}},"created_at":"2026-05-18T00:44:05.038940+00:00","updated_at":"2026-05-18T00:44:05.038940+00:00"}