{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4SZ3FTPRCHB2FKZERHHW5SCQHC","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":"f297da04f168743d14878f801ec49b111819517cb8a5ee60cc2586691e818d86","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-14T10:22:33Z","title_canon_sha256":"7df91991c5c77711f2fb50890a7cdd136349c96e3e8519f3366e45d157cb4fc0"},"schema_version":"1.0","source":{"id":"2309.07578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.07578","created_at":"2026-07-05T06:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"2309.07578v1","created_at":"2026-07-05T06:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.07578","created_at":"2026-07-05T06:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"4SZ3FTPRCHB2","created_at":"2026-07-05T06:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"4SZ3FTPRCHB2FKZE","created_at":"2026-07-05T06:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"4SZ3FTPR","created_at":"2026-07-05T06:50:45Z"}],"graph_snapshots":[{"event_id":"sha256:735b73a5008bd82f06d2d40ef11c6140681b93ab9603be6176831fdaa234bec3","target":"graph","created_at":"2026-07-05T06:50:45Z","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/2309.07578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel approach to address the challenge of generalization in offline reinforcement learning (RL), where the agent learns from a fixed dataset without any additional interaction with the environment. Specifically, we aim to improve the agent's ability to generalize to out-of-distribution goals. To achieve this, we propose to learn a dynamics model and check if it is equivariant with respect to a fixed type of transformation, namely translations in the state space. We then use an entropy regularizer to increase the equivariant set and augment the dataset with the resulting transform","authors_text":"Arunkumar Byravan, Cristina Pinneri, Jingwei Zhang, Markus Wulfmeier, Martin Riedmiller, Sarah Bechtle, William F. Whitney","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-14T10:22:33Z","title":"Equivariant Data Augmentation for Generalization in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.07578","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:e4429c7e4094b00706e32cca236bf64a4218d8b8eeec1b41cc4ca01984cde59a","target":"record","created_at":"2026-07-05T06:50:45Z","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":"f297da04f168743d14878f801ec49b111819517cb8a5ee60cc2586691e818d86","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-14T10:22:33Z","title_canon_sha256":"7df91991c5c77711f2fb50890a7cdd136349c96e3e8519f3366e45d157cb4fc0"},"schema_version":"1.0","source":{"id":"2309.07578","kind":"arxiv","version":1}},"canonical_sha256":"e4b3b2cdf111c3a2ab2489cf6ec85038be800b73202e6b0281e5c51558b04fec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4b3b2cdf111c3a2ab2489cf6ec85038be800b73202e6b0281e5c51558b04fec","first_computed_at":"2026-07-05T06:50:45.069460Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:45.069460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nn3eHOcwRPS8DFoofrs1OAYNHI5DuIt1pm8qr6wWfvjFEBxl6rH3T2JA9pagzB1p0XTKQ5xuzOgV/RHLpbbIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:45.069934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.07578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4429c7e4094b00706e32cca236bf64a4218d8b8eeec1b41cc4ca01984cde59a","sha256:735b73a5008bd82f06d2d40ef11c6140681b93ab9603be6176831fdaa234bec3"],"state_sha256":"babea343d12d527be59c05c39a6d9cc51f9ab895be8ea9b6d29f4b1fc27a7f58"}