{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OOO6Y72QGEHINEHDI3BIHDEUQ7","short_pith_number":"pith:OOO6Y72Q","canonical_record":{"source":{"id":"1906.09734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T05:37:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a3de0a2822cd07d24045140c5f64316ebb6b80946de14e1bb28124e6ad1ed01","abstract_canon_sha256":"5a1e8c2bdb72dd4485acfd639b144201e9e29545609a9434c61d8873993e8703"},"schema_version":"1.0"},"canonical_sha256":"739dec7f50310e8690e346c2838c9487ecd405cb933052d77989dd310e4c2073","source":{"kind":"arxiv","id":"1906.09734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09734","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09734v1","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09734","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"OOO6Y72QGEHI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OOO6Y72QGEHINEHD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OOO6Y72Q","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OOO6Y72QGEHINEHDI3BIHDEUQ7","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T05:37:58Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4a3de0a2822cd07d24045140c5f64316ebb6b80946de14e1bb28124e6ad1ed01","abstract_canon_sha256":"5a1e8c2bdb72dd4485acfd639b144201e9e29545609a9434c61d8873993e8703"},"schema_version":"1.0"},"canonical_sha256":"739dec7f50310e8690e346c2838c9487ecd405cb933052d77989dd310e4c2073","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:36.924203Z","signature_b64":"Tz0kVTtiuAGxTJUsqT/rAAcwAonTNVw5jARZ2nRWP3AQE5ANhUFp1Ofj2Lk54awQnQ5IrW8WTGGP4q/ZgbWdBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"739dec7f50310e8690e346c2838c9487ecd405cb933052d77989dd310e4c2073","last_reissued_at":"2026-05-17T23:42:36.923585Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:36.923585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09734","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":"2026-05-17T23:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ko/kSViKfrhJ380iPVrRTUYPpRtV5qrdlzZowGI7CfA0hmvvwYhamVmLC2b2gwWFoW0uaIAQLVnZ94K2YD5zBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T13:08:42.887607Z"},"content_sha256":"0b8b35cbcb41162e3379feecb78eda8e62489f12bf76d32c878b62ab901556de","schema_version":"1.0","event_id":"sha256:0b8b35cbcb41162e3379feecb78eda8e62489f12bf76d32c878b62ab901556de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OOO6Y72QGEHINEHDI3BIHDEUQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimal Use of Experience in First Person Shooter Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthew Aitchison","submitted_at":"2019-06-24T05:37:58Z","abstract_excerpt":"Although reinforcement learning has made great strides recently, a continuing limitation is that it requires an extremely high number of interactions with the environment. In this paper, we explore the effectiveness of reusing experience from the experience replay buffer in the Deep Q-Learning algorithm. We test the effectiveness of applying learning update steps multiple times per environmental step in the VizDoom environment and show first, this requires a change in the learning rate, and second that it does not improve the performance of the agent. Furthermore, we show that updating less fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09734","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":"2026-05-17T23:42:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qCRd4o1R0WOQNCDoDwtojXXoMgYlVT0DbnSZsYoyG5RpwzEsobGjqchmyOpQbDHQToLqzNK7hBW6bhuRCExKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T13:08:42.887956Z"},"content_sha256":"812f10696f939b2704d496dfb3cb7add6d13f103d9a21c55911e88afb43b28de","schema_version":"1.0","event_id":"sha256:812f10696f939b2704d496dfb3cb7add6d13f103d9a21c55911e88afb43b28de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/bundle.json","state_url":"https://pith.science/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/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":"2026-06-05T13:08:42Z","links":{"resolver":"https://pith.science/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7","bundle":"https://pith.science/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/bundle.json","state":"https://pith.science/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOO6Y72QGEHINEHDI3BIHDEUQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OOO6Y72QGEHINEHDI3BIHDEUQ7","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":"5a1e8c2bdb72dd4485acfd639b144201e9e29545609a9434c61d8873993e8703","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T05:37:58Z","title_canon_sha256":"4a3de0a2822cd07d24045140c5f64316ebb6b80946de14e1bb28124e6ad1ed01"},"schema_version":"1.0","source":{"id":"1906.09734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09734","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09734v1","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09734","created_at":"2026-05-17T23:42:36Z"},{"alias_kind":"pith_short_12","alias_value":"OOO6Y72QGEHI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OOO6Y72QGEHINEHD","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OOO6Y72Q","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:812f10696f939b2704d496dfb3cb7add6d13f103d9a21c55911e88afb43b28de","target":"graph","created_at":"2026-05-17T23:42:36Z","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":"Although reinforcement learning has made great strides recently, a continuing limitation is that it requires an extremely high number of interactions with the environment. In this paper, we explore the effectiveness of reusing experience from the experience replay buffer in the Deep Q-Learning algorithm. We test the effectiveness of applying learning update steps multiple times per environmental step in the VizDoom environment and show first, this requires a change in the learning rate, and second that it does not improve the performance of the agent. Furthermore, we show that updating less fr","authors_text":"Matthew Aitchison","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T05:37:58Z","title":"Optimal Use of Experience in First Person Shooter Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09734","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":"sha256:0b8b35cbcb41162e3379feecb78eda8e62489f12bf76d32c878b62ab901556de","target":"record","created_at":"2026-05-17T23:42:36Z","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":"5a1e8c2bdb72dd4485acfd639b144201e9e29545609a9434c61d8873993e8703","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T05:37:58Z","title_canon_sha256":"4a3de0a2822cd07d24045140c5f64316ebb6b80946de14e1bb28124e6ad1ed01"},"schema_version":"1.0","source":{"id":"1906.09734","kind":"arxiv","version":1}},"canonical_sha256":"739dec7f50310e8690e346c2838c9487ecd405cb933052d77989dd310e4c2073","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"739dec7f50310e8690e346c2838c9487ecd405cb933052d77989dd310e4c2073","first_computed_at":"2026-05-17T23:42:36.923585Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:36.923585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tz0kVTtiuAGxTJUsqT/rAAcwAonTNVw5jARZ2nRWP3AQE5ANhUFp1Ofj2Lk54awQnQ5IrW8WTGGP4q/ZgbWdBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:36.924203Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b8b35cbcb41162e3379feecb78eda8e62489f12bf76d32c878b62ab901556de","sha256:812f10696f939b2704d496dfb3cb7add6d13f103d9a21c55911e88afb43b28de"],"state_sha256":"48d24e1ec634c5a6aa34c4f5a3f2f3e3725bb6a259ee8cf1901e9f1abe42ef2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kIcvcF38gpF3oHMK1oYCQiFJSOn+6wKvh0hTLOrrGq7bZ49SFahIYTbr6A3YcM9YTnwOw1tVIgZYj667NcsSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T13:08:42.889894Z","bundle_sha256":"7f46549b4cf455eb8d34cc554dfe32b7706e4c9cc84e88a011df6ccf08c00984"}}