{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:K5IC6KY4T7WOKEGY45SHYX5MGO","short_pith_number":"pith:K5IC6KY4","canonical_record":{"source":{"id":"1609.05521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:52:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ff64fc6c764000f766fc371222c5262f0e8e93478247252a7ea6b3a6bd58f04","abstract_canon_sha256":"1f448ba7e8188994042c3570e29c60399435f288aef63835a9adc4ef8079b4d8"},"schema_version":"1.0"},"canonical_sha256":"57502f2b1c9fece510d8e7647c5fac33987375a84f7e3cd133ac7788ee0c1e4a","source":{"kind":"arxiv","id":"1609.05521","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05521","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05521v2","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05521","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"K5IC6KY4T7WO","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K5IC6KY4T7WOKEGY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K5IC6KY4","created_at":"2026-05-18T12:30:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:K5IC6KY4T7WOKEGY45SHYX5MGO","target":"record","payload":{"canonical_record":{"source":{"id":"1609.05521","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:52:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ff64fc6c764000f766fc371222c5262f0e8e93478247252a7ea6b3a6bd58f04","abstract_canon_sha256":"1f448ba7e8188994042c3570e29c60399435f288aef63835a9adc4ef8079b4d8"},"schema_version":"1.0"},"canonical_sha256":"57502f2b1c9fece510d8e7647c5fac33987375a84f7e3cd133ac7788ee0c1e4a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:02.212632Z","signature_b64":"dXxVIVpz/XxxJ26FfbQ8G4zrbtTYoOhtyWejuHNw/6RDfzWTtzc+wSSWkDC6XF26w6aZlToT/NbYYr9+rqXlCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57502f2b1c9fece510d8e7647c5fac33987375a84f7e3cd133ac7788ee0c1e4a","last_reissued_at":"2026-05-18T00:25:02.212209Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:02.212209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.05521","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":"2026-05-18T00:25:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duwrE7bbKfx8ic92tVNKDy8UrygsjkasfBF/909fwnblNbBMVRTx6ItwF7t3F78pRo1qLC7BHZuynuGqNYaYBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:23:43.764630Z"},"content_sha256":"6f87e576d011830b127f609a090030eb46a8bf96d214ed234ac23d68dd815f59","schema_version":"1.0","event_id":"sha256:6f87e576d011830b127f609a090030eb46a8bf96d214ed234ac23d68dd815f59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:K5IC6KY4T7WOKEGY45SHYX5MGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Playing FPS Games with Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Devendra Singh Chaplot, Guillaume Lample","submitted_at":"2016-09-18T17:52:28Z","abstract_excerpt":"Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Typically, deep reinforcement learning methods only utilize visual input for training. We present a method to augment these models to exploit game feature information such as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05521","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":"2026-05-18T00:25:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FqXbNkUU2Apo0lnKGYC9Miw11WMJrXSiT/WFyr2JME9BsBZG/9z6c88PA7tRpKhVmNQJq3aaezHr1njRqLZKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:23:43.765105Z"},"content_sha256":"59840c1c6513fffd36d50155411aa24b40634eddf442e261140ebefd0ec6f1e3","schema_version":"1.0","event_id":"sha256:59840c1c6513fffd36d50155411aa24b40634eddf442e261140ebefd0ec6f1e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/bundle.json","state_url":"https://pith.science/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/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":"2026-08-04T12:23:43Z","links":{"resolver":"https://pith.science/pith/K5IC6KY4T7WOKEGY45SHYX5MGO","bundle":"https://pith.science/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/bundle.json","state":"https://pith.science/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K5IC6KY4T7WOKEGY45SHYX5MGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:K5IC6KY4T7WOKEGY45SHYX5MGO","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":"1f448ba7e8188994042c3570e29c60399435f288aef63835a9adc4ef8079b4d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:52:28Z","title_canon_sha256":"0ff64fc6c764000f766fc371222c5262f0e8e93478247252a7ea6b3a6bd58f04"},"schema_version":"1.0","source":{"id":"1609.05521","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.05521","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"arxiv_version","alias_value":"1609.05521v2","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.05521","created_at":"2026-05-18T00:25:02Z"},{"alias_kind":"pith_short_12","alias_value":"K5IC6KY4T7WO","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_16","alias_value":"K5IC6KY4T7WOKEGY","created_at":"2026-05-18T12:30:25Z"},{"alias_kind":"pith_short_8","alias_value":"K5IC6KY4","created_at":"2026-05-18T12:30:25Z"}],"graph_snapshots":[{"event_id":"sha256:59840c1c6513fffd36d50155411aa24b40634eddf442e261140ebefd0ec6f1e3","target":"graph","created_at":"2026-05-18T00:25:02Z","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":"Advances in deep reinforcement learning have allowed autonomous agents to perform well on Atari games, often outperforming humans, using only raw pixels to make their decisions. However, most of these games take place in 2D environments that are fully observable to the agent. In this paper, we present the first architecture to tackle 3D environments in first-person shooter games, that involve partially observable states. Typically, deep reinforcement learning methods only utilize visual input for training. We present a method to augment these models to exploit game feature information such as ","authors_text":"Devendra Singh Chaplot, Guillaume Lample","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:52:28Z","title":"Playing FPS Games with Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.05521","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":"sha256:6f87e576d011830b127f609a090030eb46a8bf96d214ed234ac23d68dd815f59","target":"record","created_at":"2026-05-18T00:25:02Z","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":"1f448ba7e8188994042c3570e29c60399435f288aef63835a9adc4ef8079b4d8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-09-18T17:52:28Z","title_canon_sha256":"0ff64fc6c764000f766fc371222c5262f0e8e93478247252a7ea6b3a6bd58f04"},"schema_version":"1.0","source":{"id":"1609.05521","kind":"arxiv","version":2}},"canonical_sha256":"57502f2b1c9fece510d8e7647c5fac33987375a84f7e3cd133ac7788ee0c1e4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57502f2b1c9fece510d8e7647c5fac33987375a84f7e3cd133ac7788ee0c1e4a","first_computed_at":"2026-05-18T00:25:02.212209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:02.212209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dXxVIVpz/XxxJ26FfbQ8G4zrbtTYoOhtyWejuHNw/6RDfzWTtzc+wSSWkDC6XF26w6aZlToT/NbYYr9+rqXlCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:02.212632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.05521","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f87e576d011830b127f609a090030eb46a8bf96d214ed234ac23d68dd815f59","sha256:59840c1c6513fffd36d50155411aa24b40634eddf442e261140ebefd0ec6f1e3"],"state_sha256":"997563675660ebdd9f3fd03b79f852dd79c5baf82cfeb5c9a2524118bda34e82"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwNUQLPljJl4cI9ISME7cru8nTScjSGs9rZMDRtUTy2MYWfgq+uMoxtjACnw7GK1OlX+oHVm2MS0uHhg4nvsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:23:43.768828Z","bundle_sha256":"4a4d31a55d037437ab073f58de827f0c15ae5203e549ebe6a7db99bd1b82b219"}}