{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TAZW7GJPL7UJBORCO5YQC2A6CX","short_pith_number":"pith:TAZW7GJP","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"},"canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","source":{"kind":"arxiv","id":"1802.05944","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05944","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05944v2","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05944","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"TAZW7GJPL7UJ","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TAZW7GJPL7UJBORC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TAZW7GJP","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TAZW7GJPL7UJBORCO5YQC2A6CX","target":"record","payload":{"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"},"canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","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"},"source_kind":"arxiv","source_id":"1802.05944","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J6O4l3BQsX4OX4rRv7/m9hYwwCempcO3StDOvQuhqUsgKFZb4lvnbhkQ7JlmaexIUBlx3uM1lZCx8dr6mnYJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:27:39.395375Z"},"content_sha256":"b137c03b3d1d5464b11c10df83673cdda860e4032075c7efd8904f2ab21b6b98","schema_version":"1.0","event_id":"sha256:b137c03b3d1d5464b11c10df83673cdda860e4032075c7efd8904f2ab21b6b98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TAZW7GJPL7UJBORCO5YQC2A6CX","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r4W8S4TkgQJc2Pbh0L73kN/kGAyfYvNSibZW0UpXr+mGjZEd5arIQfFKLpT9Z8VWteGO5BWWNXUU3LX1xPyxBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T23:27:39.396097Z"},"content_sha256":"41b99e1e510ce6efb21626045cd5a638533e68d93b5d467593185495fd3c3b28","schema_version":"1.0","event_id":"sha256:41b99e1e510ce6efb21626045cd5a638533e68d93b5d467593185495fd3c3b28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/bundle.json","state_url":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T23:27:39Z","links":{"resolver":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX","bundle":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/bundle.json","state":"https://pith.science/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TAZW7GJPL7UJBORCO5YQC2A6CX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TAZW7GJPL7UJBORCO5YQC2A6CX","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":"ea934416e05795362622406a01e98cff0f480600afae8740217de40c92860cdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T14:18:46Z","title_canon_sha256":"b5be3c2323a7a7272c86c2cbb655640928b8a3fbdbd7cb66db8f75bf98df6007"},"schema_version":"1.0","source":{"id":"1802.05944","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05944","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05944v2","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05944","created_at":"2026-05-18T00:15:36Z"},{"alias_kind":"pith_short_12","alias_value":"TAZW7GJPL7UJ","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"TAZW7GJPL7UJBORC","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"TAZW7GJP","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:41b99e1e510ce6efb21626045cd5a638533e68d93b5d467593185495fd3c3b28","target":"graph","created_at":"2026-05-18T00:15:36Z","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":"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","authors_text":"Aske Plaat, Hui Wang, Michael Emmerich","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T14:18:46Z","title":"Monte Carlo Q-learning for General Game Playing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05944","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:b137c03b3d1d5464b11c10df83673cdda860e4032075c7efd8904f2ab21b6b98","target":"record","created_at":"2026-05-18T00:15:36Z","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":"ea934416e05795362622406a01e98cff0f480600afae8740217de40c92860cdd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-16T14:18:46Z","title_canon_sha256":"b5be3c2323a7a7272c86c2cbb655640928b8a3fbdbd7cb66db8f75bf98df6007"},"schema_version":"1.0","source":{"id":"1802.05944","kind":"arxiv","version":2}},"canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98336f992f5fe890ba22777101681e15d9444eede95fb047b0005e549e6a3a45","first_computed_at":"2026-05-18T00:15:36.611805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:36.611805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AUZz1RrjQCOKiDl1BE6BRNmoVYQWHUWtmV8/gMZQxR7oLLBKX7EJyGchZrGIzjMAoh2ABcbV+kdRyvKxf+gSBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:36.612515Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05944","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b137c03b3d1d5464b11c10df83673cdda860e4032075c7efd8904f2ab21b6b98","sha256:41b99e1e510ce6efb21626045cd5a638533e68d93b5d467593185495fd3c3b28"],"state_sha256":"d1159e62b97019f41c36b51a336e310e26cde1c091213a5250c4ae9137f79580"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkJtfrOHOpzMWQ3gEiTy9G9nR7Up/VGKp5L57URvY6BEJe3HPcCaohTjQiaLqfUqs4VJ5UJFbdrS0xruIciKAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T23:27:39.400080Z","bundle_sha256":"f45d757b0d5844d8a96d4d0489c93e463133ae2647a122735d1db562bb7245ec"}}