{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TAZW7GJPL7UJBORCO5YQC2A6CX","short_pith_number":"pith:TAZW7GJP","schema_version":"1.0","canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","source":{"kind":"arxiv","id":"1802.05944","version":2},"attestation_state":"computed","paper":{"title":"Monte Carlo Q-learning for General Game Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aske Plaat, Hui Wang, Michael Emmerich","submitted_at":"2018-02-16T14:18:46Z","abstract_excerpt":"After the recent groundbreaking results of AlphaGo, we have seen a strong interest in reinforcement learning in game playing. General Game Playing (GGP) provides a good testbed for reinforcement learning. In GGP, a specification of games rules is given. GGP problems can be solved by reinforcement learning. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex), to allow comparison to Banerjee et al. As expected, Q-lear"},"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":"1802.05944","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T14:18:46Z","cross_cats_sorted":[],"title_canon_sha256":"b5be3c2323a7a7272c86c2cbb655640928b8a3fbdbd7cb66db8f75bf98df6007","abstract_canon_sha256":"ea934416e05795362622406a01e98cff0f480600afae8740217de40c92860cdd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.612515Z","signature_b64":"AUZz1RrjQCOKiDl1BE6BRNmoVYQWHUWtmV8/gMZQxR7oLLBKX7EJyGchZrGIzjMAoh2ABcbV+kdRyvKxf+gSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","last_reissued_at":"2026-05-18T00:15:36.611805Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.611805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monte Carlo Q-learning for General Game Playing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aske Plaat, Hui Wang, Michael Emmerich","submitted_at":"2018-02-16T14:18:46Z","abstract_excerpt":"After the recent groundbreaking results of AlphaGo, we have seen a strong interest in reinforcement learning in game playing. General Game Playing (GGP) provides a good testbed for reinforcement learning. In GGP, a specification of games rules is given. GGP problems can be solved by reinforcement learning. Q-learning is one of the canonical reinforcement learning methods, and has been used by (Banerjee & Stone, IJCAI 2007) in GGP. In this paper we implement Q-learning in GGP for three small-board games (Tic-Tac-Toe, Connect Four, Hex), to allow comparison to Banerjee et al. As expected, Q-lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05944","kind":"arxiv","version":2},"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":"1802.05944","created_at":"2026-05-18T00:15:36.611922+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.05944v2","created_at":"2026-05-18T00:15:36.611922+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05944","created_at":"2026-05-18T00:15:36.611922+00:00"},{"alias_kind":"pith_short_12","alias_value":"TAZW7GJPL7UJ","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TAZW7GJPL7UJBORC","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TAZW7GJP","created_at":"2026-05-18T12:32:53.628368+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/TAZW7GJPL7UJBORCO5YQC2A6CX","json":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX.json","graph_json":"https://pith.science/api/pith-number/TAZW7GJPL7UJBORCO5YQC2A6CX/graph.json","events_json":"https://pith.science/api/pith-number/TAZW7GJPL7UJBORCO5YQC2A6CX/events.json","paper":"https://pith.science/paper/TAZW7GJP"},"agent_actions":{"view_html":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX","download_json":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX.json","view_paper":"https://pith.science/paper/TAZW7GJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.05944&json=true","fetch_graph":"https://pith.science/api/pith-number/TAZW7GJPL7UJBORCO5YQC2A6CX/graph.json","fetch_events":"https://pith.science/api/pith-number/TAZW7GJPL7UJBORCO5YQC2A6CX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/action/storage_attestation","attest_author":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/action/author_attestation","sign_citation":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/action/citation_signature","submit_replication":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/action/replication_record"}},"created_at":"2026-05-18T00:15:36.611922+00:00","updated_at":"2026-05-18T00:15:36.611922+00:00"}