{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QIKGNO7WECTON6WHPQDKAQYAXY","short_pith_number":"pith:QIKGNO7W","canonical_record":{"source":{"id":"1802.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T11:45:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0615a9a7d0b4c15aedc2652d65ce3b944e0780d20bd21d4b8de0d19b2271278b","abstract_canon_sha256":"0214e1dbfbc121bf3d49ad37b76e2aaacec70661b13bc1a30a7a583afcbc90b0"},"schema_version":"1.0"},"canonical_sha256":"821466bbf620a6e6fac77c06a04300be37f25951390da600ed2e585def3aa5f3","source":{"kind":"arxiv","id":"1802.06225","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06225","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06225v1","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06225","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"QIKGNO7WECTO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIKGNO7WECTON6WH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIKGNO7W","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QIKGNO7WECTON6WHPQDKAQYAXY","target":"record","payload":{"canonical_record":{"source":{"id":"1802.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T11:45:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0615a9a7d0b4c15aedc2652d65ce3b944e0780d20bd21d4b8de0d19b2271278b","abstract_canon_sha256":"0214e1dbfbc121bf3d49ad37b76e2aaacec70661b13bc1a30a7a583afcbc90b0"},"schema_version":"1.0"},"canonical_sha256":"821466bbf620a6e6fac77c06a04300be37f25951390da600ed2e585def3aa5f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:03.947751Z","signature_b64":"nPn3/+85ODZ74Ade0usFze8GJrmjSyMR+dhlZkt9HAZvlyqsKDsClOFY+JoLyWBxmAtfySeHyiIlEHQWGZ1eAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"821466bbf620a6e6fac77c06a04300be37f25951390da600ed2e585def3aa5f3","last_reissued_at":"2026-05-18T00:23:03.947170Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:03.947170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.06225","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cTsfeQnzG7qSXeqrK2hlS1ltDI3xeAsbtF4i+cxBaKwKJEyjYcDRvQPJvamsFkx6RUvkiTpQvMy7bMWl1iuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:44:58.646793Z"},"content_sha256":"b53b7f3b25f54b3d4d6b833d60fd6ca47e19e018d23025081270baff8b77d6a0","schema_version":"1.0","event_id":"sha256:b53b7f3b25f54b3d4d6b833d60fd6ca47e19e018d23025081270baff8b77d6a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QIKGNO7WECTON6WHPQDKAQYAXY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deep Q-Learning Agent for the L-Game with Variable Batch Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Petros Giannakopoulos, Yannis Cotronis","submitted_at":"2018-02-17T11:45:09Z","abstract_excerpt":"We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in order to mitigate the loss of the rare reward signal and significantly accelerate training. Despite the large action space due to the number of possible moves, the low-dimensional state space and the rarity of rewards, which only come at the end of a game, DQL is successful in training an agent capable of strong play without the use of any search methods or dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06225","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uZHApR/ZeaHdIgARA5ICElVrGbgf9AJ4giqMaopBEd041UCPFH0eQhkbiaqlMuy+ty/DrCrxkZ9AcAfTh+XFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T16:44:58.647135Z"},"content_sha256":"a0dd7db4b4a213a5b130ce374a165bd754d744695a23e95a5526c69979c48ad0","schema_version":"1.0","event_id":"sha256:a0dd7db4b4a213a5b130ce374a165bd754d744695a23e95a5526c69979c48ad0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QIKGNO7WECTON6WHPQDKAQYAXY/bundle.json","state_url":"https://pith.science/pith/QIKGNO7WECTON6WHPQDKAQYAXY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QIKGNO7WECTON6WHPQDKAQYAXY/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":"2026-07-10T16:44:58Z","links":{"resolver":"https://pith.science/pith/QIKGNO7WECTON6WHPQDKAQYAXY","bundle":"https://pith.science/pith/QIKGNO7WECTON6WHPQDKAQYAXY/bundle.json","state":"https://pith.science/pith/QIKGNO7WECTON6WHPQDKAQYAXY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QIKGNO7WECTON6WHPQDKAQYAXY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QIKGNO7WECTON6WHPQDKAQYAXY","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":"0214e1dbfbc121bf3d49ad37b76e2aaacec70661b13bc1a30a7a583afcbc90b0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T11:45:09Z","title_canon_sha256":"0615a9a7d0b4c15aedc2652d65ce3b944e0780d20bd21d4b8de0d19b2271278b"},"schema_version":"1.0","source":{"id":"1802.06225","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06225","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06225v1","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06225","created_at":"2026-05-18T00:23:03Z"},{"alias_kind":"pith_short_12","alias_value":"QIKGNO7WECTO","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QIKGNO7WECTON6WH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QIKGNO7W","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:a0dd7db4b4a213a5b130ce374a165bd754d744695a23e95a5526c69979c48ad0","target":"graph","created_at":"2026-05-18T00:23:03Z","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":"We employ the Deep Q-Learning algorithm with Experience Replay to train an agent capable of achieving a high-level of play in the L-Game while self-learning from low-dimensional states. We also employ variable batch size for training in order to mitigate the loss of the rare reward signal and significantly accelerate training. Despite the large action space due to the number of possible moves, the low-dimensional state space and the rarity of rewards, which only come at the end of a game, DQL is successful in training an agent capable of strong play without the use of any search methods or dom","authors_text":"Petros Giannakopoulos, Yannis Cotronis","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T11:45:09Z","title":"A Deep Q-Learning Agent for the L-Game with Variable Batch Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06225","kind":"arxiv","version":1},"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:b53b7f3b25f54b3d4d6b833d60fd6ca47e19e018d23025081270baff8b77d6a0","target":"record","created_at":"2026-05-18T00:23:03Z","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":"0214e1dbfbc121bf3d49ad37b76e2aaacec70661b13bc1a30a7a583afcbc90b0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-17T11:45:09Z","title_canon_sha256":"0615a9a7d0b4c15aedc2652d65ce3b944e0780d20bd21d4b8de0d19b2271278b"},"schema_version":"1.0","source":{"id":"1802.06225","kind":"arxiv","version":1}},"canonical_sha256":"821466bbf620a6e6fac77c06a04300be37f25951390da600ed2e585def3aa5f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"821466bbf620a6e6fac77c06a04300be37f25951390da600ed2e585def3aa5f3","first_computed_at":"2026-05-18T00:23:03.947170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:03.947170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nPn3/+85ODZ74Ade0usFze8GJrmjSyMR+dhlZkt9HAZvlyqsKDsClOFY+JoLyWBxmAtfySeHyiIlEHQWGZ1eAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:03.947751Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06225","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b53b7f3b25f54b3d4d6b833d60fd6ca47e19e018d23025081270baff8b77d6a0","sha256:a0dd7db4b4a213a5b130ce374a165bd754d744695a23e95a5526c69979c48ad0"],"state_sha256":"d90e38d592e8d6a9f4ec628a302d7408f9077d64ed1acbfadea637f93fdef4d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z1gsT40pkF2CCCxYNwAuCTkwbCMUEfTUWsuLImvxO7nyfdJSyq9r2XJvRJRL9Z3h+GVivFakFL13wsChnpe6Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T16:44:58.649358Z","bundle_sha256":"4c8fbee3db92529c0fe660ad7bff4a8941199a6673455d12b4e03a41b1f3e115"}}