{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:O644I7OLWL3GAWVYUNSM2B26EO","short_pith_number":"pith:O644I7OL","schema_version":"1.0","canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","source":{"kind":"arxiv","id":"1806.05117","version":1},"attestation_state":"computed","paper":{"title":"Learning to Shoot in First Person Shooter Games by Stabilizing Actions and Clustering Rewards for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Frank G. Glavin, Michael G. Madden","submitted_at":"2018-06-13T15:41:34Z","abstract_excerpt":"While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the time that elapses between deciding to take an action and receiving a reward based on its outcome can be longer than the interval between successive decisions. We explore this in the context of a non-player character (NPC) in a modern first-person shooter game. Such games take place in 3D environments where players, both human and computer-controlled, compete by"},"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":"1806.05117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-13T15:41:34Z","cross_cats_sorted":[],"title_canon_sha256":"f6b8ff83ba7d73a0826a5526254e2ff9df550752d6ee63570ea5cc769039ebf8","abstract_canon_sha256":"31d0a01e7a35c0f6cdec38f007b2cd4ca5003402b80e5e5e5bacb732b867a683"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:20.095566Z","signature_b64":"WP5J/13wBKytIDYHEAe9TtRi2iqf0NbXq6V9olM8ir+FAcCfIlMZgZU53QY5IQyGR+ChAxnUUtgv6gLc2206AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77b9c47dcbb2f6605ab8a364cd075e23a30b9125fd68cce060dc748878c27796","last_reissued_at":"2026-05-18T00:13:20.094931Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:20.094931Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Shoot in First Person Shooter Games by Stabilizing Actions and Clustering Rewards for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Frank G. Glavin, Michael G. Madden","submitted_at":"2018-06-13T15:41:34Z","abstract_excerpt":"While reinforcement learning (RL) has been applied to turn-based board games for many years, more complex games involving decision-making in real-time are beginning to receive more attention. A challenge in such environments is that the time that elapses between deciding to take an action and receiving a reward based on its outcome can be longer than the interval between successive decisions. We explore this in the context of a non-player character (NPC) in a modern first-person shooter game. Such games take place in 3D environments where players, both human and computer-controlled, compete by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05117","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":"1806.05117","created_at":"2026-05-18T00:13:20.095014+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05117v1","created_at":"2026-05-18T00:13:20.095014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05117","created_at":"2026-05-18T00:13:20.095014+00:00"},{"alias_kind":"pith_short_12","alias_value":"O644I7OLWL3G","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"O644I7OLWL3GAWVY","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"O644I7OL","created_at":"2026-05-18T12:32:43.782077+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/O644I7OLWL3GAWVYUNSM2B26EO","json":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO.json","graph_json":"https://pith.science/api/pith-number/O644I7OLWL3GAWVYUNSM2B26EO/graph.json","events_json":"https://pith.science/api/pith-number/O644I7OLWL3GAWVYUNSM2B26EO/events.json","paper":"https://pith.science/paper/O644I7OL"},"agent_actions":{"view_html":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO","download_json":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO.json","view_paper":"https://pith.science/paper/O644I7OL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05117&json=true","fetch_graph":"https://pith.science/api/pith-number/O644I7OLWL3GAWVYUNSM2B26EO/graph.json","fetch_events":"https://pith.science/api/pith-number/O644I7OLWL3GAWVYUNSM2B26EO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/action/storage_attestation","attest_author":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/action/author_attestation","sign_citation":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/action/citation_signature","submit_replication":"https://pith.science/pith/O644I7OLWL3GAWVYUNSM2B26EO/action/replication_record"}},"created_at":"2026-05-18T00:13:20.095014+00:00","updated_at":"2026-05-18T00:13:20.095014+00:00"}