{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HDMAL5CAOZHLPXRNZRTLTIX4ZW","short_pith_number":"pith:HDMAL5CA","schema_version":"1.0","canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","source":{"kind":"arxiv","id":"1810.08163","version":1},"attestation_state":"computed","paper":{"title":"Fast deep reinforcement learning using online adjustments from the past","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Pritzel, Andr\\'e Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen","submitted_at":"2018-10-18T17:00:20Z","abstract_excerpt":"We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games."},"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":"1810.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-18T17:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5920a5261091efac7ccf22bdd32543594d3dae9bdfa1182e35e1c19704456981","abstract_canon_sha256":"deee04dc6ebc34e1edc4edb504211ed5574fe36d322645e3fd42723968534415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:50.410486Z","signature_b64":"2QlZAIey9JvZae9Xm3pdqqfCPbYBuSqnx+NeXzC71DSotCGj1FLZJsBU8u5HWle4mULjYg7RKcmCdEWdjzYtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38d805f440764eb7de2dcc66b9a2fccd8890b1ccca19f4bae872bd3ee35c3a10","last_reissued_at":"2026-05-18T00:02:50.409991Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:50.409991Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast deep reinforcement learning using online adjustments from the past","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alexander Pritzel, Andr\\'e Barreto, Charles Blundell, Pablo Sprechmann, Steven Hansen","submitted_at":"2018-10-18T17:00:20Z","abstract_excerpt":"We propose Ephemeral Value Adjusments (EVA): a means of allowing deep reinforcement learning agents to rapidly adapt to experience in their replay buffer. EVA shifts the value predicted by a neural network with an estimate of the value function found by planning over experience tuples from the replay buffer near the current state. EVA combines a number of recent ideas around combining episodic memory-like structures into reinforcement learning agents: slot-based storage, content-based retrieval, and memory-based planning. We show that EVAis performant on a demonstration task and Atari games."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08163","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":"1810.08163","created_at":"2026-05-18T00:02:50.410067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.08163v1","created_at":"2026-05-18T00:02:50.410067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08163","created_at":"2026-05-18T00:02:50.410067+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDMAL5CAOZHL","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDMAL5CAOZHLPXRN","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDMAL5CA","created_at":"2026-05-18T12:32:28.185984+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/HDMAL5CAOZHLPXRNZRTLTIX4ZW","json":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW.json","graph_json":"https://pith.science/api/pith-number/HDMAL5CAOZHLPXRNZRTLTIX4ZW/graph.json","events_json":"https://pith.science/api/pith-number/HDMAL5CAOZHLPXRNZRTLTIX4ZW/events.json","paper":"https://pith.science/paper/HDMAL5CA"},"agent_actions":{"view_html":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW","download_json":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW.json","view_paper":"https://pith.science/paper/HDMAL5CA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.08163&json=true","fetch_graph":"https://pith.science/api/pith-number/HDMAL5CAOZHLPXRNZRTLTIX4ZW/graph.json","fetch_events":"https://pith.science/api/pith-number/HDMAL5CAOZHLPXRNZRTLTIX4ZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/action/storage_attestation","attest_author":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/action/author_attestation","sign_citation":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/action/citation_signature","submit_replication":"https://pith.science/pith/HDMAL5CAOZHLPXRNZRTLTIX4ZW/action/replication_record"}},"created_at":"2026-05-18T00:02:50.410067+00:00","updated_at":"2026-05-18T00:02:50.410067+00:00"}