{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:B6H6XRM6RWZSBL7F3HTOWHUWJ2","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":"892498aab54099109d6e744c83c867cbc379de8aba7b1aba1d04b47a75ef025d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T10:29:46Z","title_canon_sha256":"8de4c7169bbee4c291421ca061d14b97157f8cac24a4d696ff52d333dc147abd"},"schema_version":"1.0","source":{"id":"2402.05546","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05546","created_at":"2026-07-05T07:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05546v1","created_at":"2026-07-05T07:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05546","created_at":"2026-07-05T07:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"B6H6XRM6RWZS","created_at":"2026-07-05T07:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"B6H6XRM6RWZSBL7F","created_at":"2026-07-05T07:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"B6H6XRM6","created_at":"2026-07-05T07:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:5c9ff8ad51f2545dad6e4234617eadbcce7564308449561c4ec1a0aa705213a0","target":"graph","created_at":"2026-07-05T07:42:52Z","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/2402.05546/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that offline actor-critic algorithms can outperform strong, supervised, behavioral cloning baselines for multi-task training on a large dataset containing both sub-optimal and expert behavior on 132 continuous control tasks. We introduce a Perceiver-based actor-critic model and elucidate the key model features needed to make offline RL work with self- and cross-attention modules. Overall, we find that: i) simple offline act","authors_text":"Abbas Abdolmaleki, Jingwei Zhang, Jost Tobias Springenberg, Martin Riedmiller, Michael Bloesch, Nicolas Heess, Oliver Groth, Philemon Brakel, Roland Hafner, Sarah Bechtle, Steven Kapturowski, Thomas Lampe","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T10:29:46Z","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05546","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:d91803021ff517df91da8dc09ce52e44357a381d6701faa845a8e2ca0bd5110b","target":"record","created_at":"2026-07-05T07:42:52Z","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":"892498aab54099109d6e744c83c867cbc379de8aba7b1aba1d04b47a75ef025d","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-08T10:29:46Z","title_canon_sha256":"8de4c7169bbee4c291421ca061d14b97157f8cac24a4d696ff52d333dc147abd"},"schema_version":"1.0","source":{"id":"2402.05546","kind":"arxiv","version":1}},"canonical_sha256":"0f8febc59e8db320afe5d9e6eb1e964e84131612a4db9a64ce1e1d09f1425fa1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f8febc59e8db320afe5d9e6eb1e964e84131612a4db9a64ce1e1d09f1425fa1","first_computed_at":"2026-07-05T07:42:52.262145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:52.262145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I6L39MfiDeGJOgQv7AjfT9Gvp7oqtHGUMP1Ff/+r+8a87tnNf77R2Kt3dqzO412xs1RalXCZna2/ZZwRVSQXCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:52.262589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05546","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d91803021ff517df91da8dc09ce52e44357a381d6701faa845a8e2ca0bd5110b","sha256:5c9ff8ad51f2545dad6e4234617eadbcce7564308449561c4ec1a0aa705213a0"],"state_sha256":"af673321db5b1a7235f312326752f8e2aa9601dcd7be1646f91521c502b170b5"}