{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:K4XTAVJCGISFTCMHET53YPQ6MQ","short_pith_number":"pith:K4XTAVJC","schema_version":"1.0","canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","source":{"kind":"arxiv","id":"1801.03138","version":1},"attestation_state":"computed","paper":{"title":"Deep In-GPU Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Parr","submitted_at":"2018-01-09T20:52:33Z","abstract_excerpt":"Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copied from the CPU. I trained an agent to play Super Smash Bros. Melee, using internal game memory values as inputs and outputting controller button presses. A single state in Melee contains 27 floats, so t"},"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":"1801.03138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-01-09T20:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"66cbd9db7104f00df1d5552c38d5c1c389552d62579c72ba153d0ad513ffc5e1","abstract_canon_sha256":"ea9018b533bc89a5f13be493f12f846fa7413305820a3598c27a01c7fcfb46ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:18.920396Z","signature_b64":"tIjNZbKSzpkNFqnhIROBfcPYUjhkQAjYwwCzs1jKZL4IIlzhwFh4AFRajL/psUj1PJiLtAwC2KTNbZztbez9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"572f305522322459898724fbbc3e1e641e1de7bd0322235c703afebd7662077a","last_reissued_at":"2026-05-18T00:26:18.919391Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:18.919391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep In-GPU Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Parr","submitted_at":"2018-01-09T20:52:33Z","abstract_excerpt":"Experience replay allows a reinforcement learning agent to train on samples from a large amount of the most recent experiences. A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training. I moved this list to the GPU, thus creating an in-GPU experience replay, and a training step that no longer has inputs copied from the CPU. I trained an agent to play Super Smash Bros. Melee, using internal game memory values as inputs and outputting controller button presses. A single state in Melee contains 27 floats, so t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.03138","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":"1801.03138","created_at":"2026-05-18T00:26:18.919703+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.03138v1","created_at":"2026-05-18T00:26:18.919703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.03138","created_at":"2026-05-18T00:26:18.919703+00:00"},{"alias_kind":"pith_short_12","alias_value":"K4XTAVJCGISF","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"K4XTAVJCGISFTCMH","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"K4XTAVJC","created_at":"2026-05-18T12:32:33.847187+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/K4XTAVJCGISFTCMHET53YPQ6MQ","json":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ.json","graph_json":"https://pith.science/api/pith-number/K4XTAVJCGISFTCMHET53YPQ6MQ/graph.json","events_json":"https://pith.science/api/pith-number/K4XTAVJCGISFTCMHET53YPQ6MQ/events.json","paper":"https://pith.science/paper/K4XTAVJC"},"agent_actions":{"view_html":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ","download_json":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ.json","view_paper":"https://pith.science/paper/K4XTAVJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.03138&json=true","fetch_graph":"https://pith.science/api/pith-number/K4XTAVJCGISFTCMHET53YPQ6MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/K4XTAVJCGISFTCMHET53YPQ6MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/action/storage_attestation","attest_author":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/action/author_attestation","sign_citation":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/action/citation_signature","submit_replication":"https://pith.science/pith/K4XTAVJCGISFTCMHET53YPQ6MQ/action/replication_record"}},"created_at":"2026-05-18T00:26:18.919703+00:00","updated_at":"2026-05-18T00:26:18.919703+00:00"}