{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BPZWB572KDES7IGKI3FQEXWVTE","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":"af8bb0f6fbce555e3809df5af104b7a98e5d9663b60dc017b7dd5fedbbf9d951","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T04:01:17Z","title_canon_sha256":"d99ed3a1aacaaf1e55c47484c34b9601c91aa195495e8201cdec53950b8fbeca"},"schema_version":"1.0","source":{"id":"2501.12620","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.12620","created_at":"2026-07-05T10:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.12620v1","created_at":"2026-07-05T10:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.12620","created_at":"2026-07-05T10:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"BPZWB572KDES","created_at":"2026-07-05T10:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"BPZWB572KDES7IGK","created_at":"2026-07-05T10:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"BPZWB572","created_at":"2026-07-05T10:03:55Z"}],"graph_snapshots":[{"event_id":"sha256:a8e8629491b76d83b594b584eb98b0e86d06f6fa7e80ab31e42bc67207700093","target":"graph","created_at":"2026-07-05T10:03:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.12620/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce ADEPT: Adaptive Data ExPloiTation, a simple yet powerful framework to enhance the **data efficiency** and **generalization** in deep reinforcement learning (RL). Specifically, ADEPT adaptively manages the use of sampled data across different learning stages via multi-armed bandit (MAB) algorithms, optimizing data utilization while mitigating overfitting. Moreover, ADEPT can significantly reduce the computational overhead and accelerate a wide range of RL algorithms. We test ADEPT on benchmarks including Procgen, MiniGrid, and PyBullet. Extensive simulation demonstrates that ADEPT ","authors_text":"Bo Li, Mingqi Yuan, Wenjun Zeng, Xin Jin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T04:01:17Z","title":"Adaptive Data Exploitation in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.12620","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":"sha256:16b748f5f53614aa326e4f27da20e0550c32aebdec92cdea8ecb0532d33a187a","target":"record","created_at":"2026-07-05T10:03:55Z","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":"af8bb0f6fbce555e3809df5af104b7a98e5d9663b60dc017b7dd5fedbbf9d951","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T04:01:17Z","title_canon_sha256":"d99ed3a1aacaaf1e55c47484c34b9601c91aa195495e8201cdec53950b8fbeca"},"schema_version":"1.0","source":{"id":"2501.12620","kind":"arxiv","version":1}},"canonical_sha256":"0bf360f7fa50c92fa0ca46cb025ed5991fb129fba4844ee741ab447304c49e31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf360f7fa50c92fa0ca46cb025ed5991fb129fba4844ee741ab447304c49e31","first_computed_at":"2026-07-05T10:03:55.829956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:55.829956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gSBtJGKZ8EKlWETMH86+PXZC7kDbSDv1HUrN25098aSAhUB96/qhu6uKCMDWmfkubZE0O5jFCAOLclPquigkDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:55.830581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.12620","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16b748f5f53614aa326e4f27da20e0550c32aebdec92cdea8ecb0532d33a187a","sha256:a8e8629491b76d83b594b584eb98b0e86d06f6fa7e80ab31e42bc67207700093"],"state_sha256":"8a5457094c1bf2ff7b0fd7bb60a309883c976245bd93a728e6f97cdcf76fa4bf"}