{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:LKQIUL5AN6UN22T4C6LLH5Y6MR","short_pith_number":"pith:LKQIUL5A","canonical_record":{"source":{"id":"1712.01275","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T06:03:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec477ffd581c8aa6df5c6933dafe65c90db00ce75ff74c48733f7acffd1afda6","abstract_canon_sha256":"30ee412241bc54c522af2fb4538e6add3b9e0b308a22b1762faa6159b8af371c"},"schema_version":"1.0"},"canonical_sha256":"5aa08a2fa06fa8dd6a7c1796b3f71e645d4ade85e57eed5fdb7599e0445da838","source":{"kind":"arxiv","id":"1712.01275","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01275","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01275v3","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01275","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"LKQIUL5AN6UN","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LKQIUL5AN6UN22T4","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LKQIUL5A","created_at":"2026-05-18T12:31:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:LKQIUL5AN6UN22T4C6LLH5Y6MR","target":"record","payload":{"canonical_record":{"source":{"id":"1712.01275","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T06:03:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ec477ffd581c8aa6df5c6933dafe65c90db00ce75ff74c48733f7acffd1afda6","abstract_canon_sha256":"30ee412241bc54c522af2fb4538e6add3b9e0b308a22b1762faa6159b8af371c"},"schema_version":"1.0"},"canonical_sha256":"5aa08a2fa06fa8dd6a7c1796b3f71e645d4ade85e57eed5fdb7599e0445da838","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:18.861072Z","signature_b64":"SNevF4nTEppdh5GRyUTVymSP8vFBj4LxtQ3HpYEtcvYH24NYyAHGFlB5AyRL2/TvPI7FuvDYSQWRxRkMyCMDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5aa08a2fa06fa8dd6a7c1796b3f71e645d4ade85e57eed5fdb7599e0445da838","last_reissued_at":"2026-05-18T00:17:18.860569Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:18.860569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.01275","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBrDvgzZo0cXmkAodkhDKT3dZOZHheN5OL+4QbZaSWXOJnoktfvLtyhdrvoj/mfozz2vl7byapqT08oGlawcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:33:48.203345Z"},"content_sha256":"d8cc7049cf8289274bae8c6053256146839d9664747b80e4ee20c7adc8a85b8b","schema_version":"1.0","event_id":"sha256:d8cc7049cf8289274bae8c6053256146839d9664747b80e4ee20c7adc8a85b8b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:LKQIUL5AN6UN22T4C6LLH5Y6MR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Deeper Look at Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Richard S. Sutton, Shangtong Zhang","submitted_at":"2017-12-04T06:03:26Z","abstract_excerpt":"Recently experience replay is widely used in various deep reinforcement learning (RL) algorithms, in this paper we rethink the utility of experience replay. It introduces a new hyper-parameter, the memory buffer size, which needs carefully tuning. However unfortunately the importance of this new hyper-parameter has been underestimated in the community for a long time. In this paper we did a systematic empirical study of experience replay under various function representations. We showcase that a large replay buffer can significantly hurt the performance. Moreover, we propose a simple O(1) meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01275","kind":"arxiv","version":3},"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":"2026-05-18T00:17:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPHwnZjZfXnpFP5NDH3L76i3ZKF9+pmfKIQvDg0aPKMSoLJhTxZHinSNCP8qQgaxrNhgFjUBkSi7zha94+OGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T02:33:48.203734Z"},"content_sha256":"372560701265f2a91cded800e60a6e30c8daa50b2a7031fb78b7d9232cfdf88a","schema_version":"1.0","event_id":"sha256:372560701265f2a91cded800e60a6e30c8daa50b2a7031fb78b7d9232cfdf88a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/bundle.json","state_url":"https://pith.science/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/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":"2026-06-05T02:33:48Z","links":{"resolver":"https://pith.science/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR","bundle":"https://pith.science/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/bundle.json","state":"https://pith.science/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LKQIUL5AN6UN22T4C6LLH5Y6MR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:LKQIUL5AN6UN22T4C6LLH5Y6MR","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":"30ee412241bc54c522af2fb4538e6add3b9e0b308a22b1762faa6159b8af371c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T06:03:26Z","title_canon_sha256":"ec477ffd581c8aa6df5c6933dafe65c90db00ce75ff74c48733f7acffd1afda6"},"schema_version":"1.0","source":{"id":"1712.01275","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.01275","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"arxiv_version","alias_value":"1712.01275v3","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.01275","created_at":"2026-05-18T00:17:18Z"},{"alias_kind":"pith_short_12","alias_value":"LKQIUL5AN6UN","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_16","alias_value":"LKQIUL5AN6UN22T4","created_at":"2026-05-18T12:31:28Z"},{"alias_kind":"pith_short_8","alias_value":"LKQIUL5A","created_at":"2026-05-18T12:31:28Z"}],"graph_snapshots":[{"event_id":"sha256:372560701265f2a91cded800e60a6e30c8daa50b2a7031fb78b7d9232cfdf88a","target":"graph","created_at":"2026-05-18T00:17:18Z","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":"Recently experience replay is widely used in various deep reinforcement learning (RL) algorithms, in this paper we rethink the utility of experience replay. It introduces a new hyper-parameter, the memory buffer size, which needs carefully tuning. However unfortunately the importance of this new hyper-parameter has been underestimated in the community for a long time. In this paper we did a systematic empirical study of experience replay under various function representations. We showcase that a large replay buffer can significantly hurt the performance. Moreover, we propose a simple O(1) meth","authors_text":"Richard S. Sutton, Shangtong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T06:03:26Z","title":"A Deeper Look at Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.01275","kind":"arxiv","version":3},"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:d8cc7049cf8289274bae8c6053256146839d9664747b80e4ee20c7adc8a85b8b","target":"record","created_at":"2026-05-18T00:17:18Z","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":"30ee412241bc54c522af2fb4538e6add3b9e0b308a22b1762faa6159b8af371c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-12-04T06:03:26Z","title_canon_sha256":"ec477ffd581c8aa6df5c6933dafe65c90db00ce75ff74c48733f7acffd1afda6"},"schema_version":"1.0","source":{"id":"1712.01275","kind":"arxiv","version":3}},"canonical_sha256":"5aa08a2fa06fa8dd6a7c1796b3f71e645d4ade85e57eed5fdb7599e0445da838","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5aa08a2fa06fa8dd6a7c1796b3f71e645d4ade85e57eed5fdb7599e0445da838","first_computed_at":"2026-05-18T00:17:18.860569Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:18.860569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNevF4nTEppdh5GRyUTVymSP8vFBj4LxtQ3HpYEtcvYH24NYyAHGFlB5AyRL2/TvPI7FuvDYSQWRxRkMyCMDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:18.861072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.01275","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8cc7049cf8289274bae8c6053256146839d9664747b80e4ee20c7adc8a85b8b","sha256:372560701265f2a91cded800e60a6e30c8daa50b2a7031fb78b7d9232cfdf88a"],"state_sha256":"dcd16b12b64d7ee84fb48c184f4b09e7926b6d952d1ebf5433b76db7b7d37be8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kDUYstDBwpwUUtlyKSW89unnwLlSkUle1rBsx8uUAbQxFhkDUWJcZ55RP7VP81BWzTildjJZdGGd7nv99asPCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T02:33:48.205735Z","bundle_sha256":"0116f0e1338f1da8cba8003fac757f66e741a185e9ae440a828cf68db48e807f"}}