{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7V4U452UWPZF45WFC66VLPAEJU","short_pith_number":"pith:7V4U452U","schema_version":"1.0","canonical_sha256":"fd794e7754b3f25e76c517bd55bc044d1eb2c4d862b3737a4dd9e7cfa784e8f1","source":{"kind":"arxiv","id":"1912.13465","version":1},"attestation_state":"computed","paper":{"title":"Reward-Conditioned Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviral Kumar, Sergey Levine, Xue Bin Peng","submitted_at":"2019-12-31T18:07:43Z","abstract_excerpt":"Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle, difficult to use and tune, and sensitive to seemingly innocuous implementation decisions. In contrast, imitation learning utilizes standard and well-understood supervised learning methods, but requires near-optimal expert data. Can we learn effective policies via supervised learning without demonstrations? The main idea that we explore in this work is that non-e"},"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":"1912.13465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-31T18:07:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b10c8592e6831626aa4684c15bae1f033177e1e6a9b761cdbb39ea0eeb1e327e","abstract_canon_sha256":"a9e91743ec816287060cba04d412500cd75b1b5ed564ba34849b05e4eeb187d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:08.908862Z","signature_b64":"X0IFOZergPDyvHofPU7kbNQktkFlrTPkH9b4PtlKHAvaQ6S/0TnjXjJmG1P5P9aaZDvGcyeGbp/Jox+j5fvcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd794e7754b3f25e76c517bd55bc044d1eb2c4d862b3737a4dd9e7cfa784e8f1","last_reissued_at":"2026-07-05T00:29:08.908527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:08.908527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Conditioned Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aviral Kumar, Sergey Levine, Xue Bin Peng","submitted_at":"2019-12-31T18:07:43Z","abstract_excerpt":"Reinforcement learning offers the promise of automating the acquisition of complex behavioral skills. However, compared to commonly used and well-understood supervised learning methods, reinforcement learning algorithms can be brittle, difficult to use and tune, and sensitive to seemingly innocuous implementation decisions. In contrast, imitation learning utilizes standard and well-understood supervised learning methods, but requires near-optimal expert data. Can we learn effective policies via supervised learning without demonstrations? The main idea that we explore in this work is that non-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.13465","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1912.13465/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":"1912.13465","created_at":"2026-07-05T00:29:08.908583+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.13465v1","created_at":"2026-07-05T00:29:08.908583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.13465","created_at":"2026-07-05T00:29:08.908583+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V4U452UWPZF","created_at":"2026-07-05T00:29:08.908583+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V4U452UWPZF45WF","created_at":"2026-07-05T00:29:08.908583+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V4U452U","created_at":"2026-07-05T00:29:08.908583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24231","citing_title":"FlowR2A: Learning Reward-to-Action Distribution for Multimodal Driving Planning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11087","citing_title":"Test-Time Gradient Guidance of Flow Policies in Reinforcement Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08312","citing_title":"Neuro-Symbolic Injection of LTLf Constraints in Autoregressive Reinforcement Learning Policies","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05414","citing_title":"When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32027","citing_title":"Freeform Preference Learning for Robotic Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2106.01345","citing_title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14759","citing_title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":77,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU","json":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU.json","graph_json":"https://pith.science/api/pith-number/7V4U452UWPZF45WFC66VLPAEJU/graph.json","events_json":"https://pith.science/api/pith-number/7V4U452UWPZF45WFC66VLPAEJU/events.json","paper":"https://pith.science/paper/7V4U452U"},"agent_actions":{"view_html":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU","download_json":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU.json","view_paper":"https://pith.science/paper/7V4U452U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.13465&json=true","fetch_graph":"https://pith.science/api/pith-number/7V4U452UWPZF45WFC66VLPAEJU/graph.json","fetch_events":"https://pith.science/api/pith-number/7V4U452UWPZF45WFC66VLPAEJU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU/action/storage_attestation","attest_author":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU/action/author_attestation","sign_citation":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU/action/citation_signature","submit_replication":"https://pith.science/pith/7V4U452UWPZF45WFC66VLPAEJU/action/replication_record"}},"created_at":"2026-07-05T00:29:08.908583+00:00","updated_at":"2026-07-05T00:29:08.908583+00:00"}