{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:57I7V4MYMOUOJUZHT6QM5IRKFJ","short_pith_number":"pith:57I7V4MY","schema_version":"1.0","canonical_sha256":"efd1faf19863a8e4d3279fa0cea22a2a6282b5235eaf12038793a54f54ab72d7","source":{"kind":"arxiv","id":"2410.20092","version":2},"attestation_state":"computed","paper":{"title":"OGBench: Benchmarking Offline Goal-Conditioned RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Kevin Frans, Seohong Park, Sergey Levine","submitted_at":"2024-10-26T06:06:08Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference im"},"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":"2410.20092","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-26T06:06:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"66fc598703407b2bdd92f5c38d7d611703cc1ed610cc307fe1582ad3638a967c","abstract_canon_sha256":"bd7d4fd4df48f728e4e4241d9e8130214d9ef49f20778b1ec7bc66921738c187"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:44.391567Z","signature_b64":"c10UnVIgtRHkz44mqAn3/52Cc3kkjVVsKiG8eWKKxHeRHzgcx7bEG5I9HZRoPkq78RpXtwc5u2PQs0XVh1TWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd1faf19863a8e4d3279fa0cea22a2a6282b5235eaf12038793a54f54ab72d7","last_reissued_at":"2026-07-05T10:13:44.390978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:44.390978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OGBench: Benchmarking Offline Goal-Conditioned RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Kevin Frans, Seohong Park, Sergey Levine","submitted_at":"2024-10-26T06:06:08Z","abstract_excerpt":"Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without rewards. Despite the importance of this setting, we lack a standard benchmark that can systematically evaluate the capabilities of offline GCRL algorithms. In this work, we propose OGBench, a new, high-quality benchmark for algorithms research in offline goal-conditioned RL. OGBench consists of 8 types of environments, 85 datasets, and reference im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20092","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.20092/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2410.20092","created_at":"2026-07-05T10:13:44.391059+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20092v2","created_at":"2026-07-05T10:13:44.391059+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20092","created_at":"2026-07-05T10:13:44.391059+00:00"},{"alias_kind":"pith_short_12","alias_value":"57I7V4MYMOUO","created_at":"2026-07-05T10:13:44.391059+00:00"},{"alias_kind":"pith_short_16","alias_value":"57I7V4MYMOUOJUZH","created_at":"2026-07-05T10:13:44.391059+00:00"},{"alias_kind":"pith_short_8","alias_value":"57I7V4MY","created_at":"2026-07-05T10:13:44.391059+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11087","citing_title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23551","citing_title":"Goal-Conditioned Agents that Learn Everything All at Once","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22711","citing_title":"Abstraction for Offline Goal-Conditioned Reinforcement Learning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00333","citing_title":"Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07969","citing_title":"Reinforcement Learning with Action Chunking","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09580","citing_title":"SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13554","citing_title":"Self-Supervised On-Policy Reinforcement Learning via Contrastive Proximal Policy Optimisation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03208","citing_title":"Hierarchical Planning with Latent World Models","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12416","citing_title":"Aligning Flow Map Policies with Optimal Q-Guidance","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09364","citing_title":"Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24729","citing_title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05812","citing_title":"Long-Horizon Q-Learning: Accurate Value Learning via n-Step Inequalities","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00333","citing_title":"Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01663","citing_title":"Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08960","citing_title":"Efficient Hierarchical Implicit Flow Q-learning for Offline Goal-conditioned Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07278","citing_title":"Predictive but Not Plannable: RC-aux for Latent World Models","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17919","citing_title":"Fisher Decorator: Refining Flow Policy via a Local Transport Map","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20627","citing_title":"Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ","json":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ.json","graph_json":"https://pith.science/api/pith-number/57I7V4MYMOUOJUZHT6QM5IRKFJ/graph.json","events_json":"https://pith.science/api/pith-number/57I7V4MYMOUOJUZHT6QM5IRKFJ/events.json","paper":"https://pith.science/paper/57I7V4MY"},"agent_actions":{"view_html":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ","download_json":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ.json","view_paper":"https://pith.science/paper/57I7V4MY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20092&json=true","fetch_graph":"https://pith.science/api/pith-number/57I7V4MYMOUOJUZHT6QM5IRKFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/57I7V4MYMOUOJUZHT6QM5IRKFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ/action/storage_attestation","attest_author":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ/action/author_attestation","sign_citation":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ/action/citation_signature","submit_replication":"https://pith.science/pith/57I7V4MYMOUOJUZHT6QM5IRKFJ/action/replication_record"}},"created_at":"2026-07-05T10:13:44.391059+00:00","updated_at":"2026-07-05T10:13:44.391059+00:00"}