{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5SHGPZMLNH7YKDKIHNGMGI6KHI","short_pith_number":"pith:5SHGPZML","schema_version":"1.0","canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","source":{"kind":"arxiv","id":"1705.07798","version":1},"attestation_state":"computed","paper":{"title":"A unified view of entropy-regularized Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Gergely Neu, Vicen\\c{c} G\\'omez","submitted_at":"2017-05-22T15:06:25Z","abstract_excerpt":"We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to accommodate convex regularization functions. Our key result is showing that using the conditional entropy of the joint state-action distributions as regularization yields a dual optimization problem closely resembling the Bellman optimality equations. This result enables us to formalize a number of state-of-the-art entropy-regularized reinforcement learning algori"},"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":"1705.07798","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-22T15:06:25Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"34012cc621064e4e53b898ca3a72dab160de80b2c219c0bf5bd94fb289fc0716","abstract_canon_sha256":"942caccdb968f4cb5a9d181a01bbc15016e0a58164c8017cfd187e00b822889c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:44:04.537166Z","signature_b64":"Q3VBA/ymPpHbMDDdxZ2GCFVAkbJDnFOUtOHWKFsAVPI+HNWO0oz4XJupCgwXEshifIPxipFuSzNJYBO9WmGdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec8e67e58b69ff850d483b4cc323ca3a34900f8e2738ff3c4f4bf6120482ca37","last_reissued_at":"2026-05-18T00:44:04.536622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:44:04.536622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A unified view of entropy-regularized Markov decision processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Gergely Neu, Vicen\\c{c} G\\'omez","submitted_at":"2017-05-22T15:06:25Z","abstract_excerpt":"We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to accommodate convex regularization functions. Our key result is showing that using the conditional entropy of the joint state-action distributions as regularization yields a dual optimization problem closely resembling the Bellman optimality equations. This result enables us to formalize a number of state-of-the-art entropy-regularized reinforcement learning algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07798","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":""},"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":"1705.07798","created_at":"2026-05-18T00:44:04.536701+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.07798v1","created_at":"2026-05-18T00:44:04.536701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07798","created_at":"2026-05-18T00:44:04.536701+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SHGPZMLNH7Y","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SHGPZMLNH7YKDKI","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SHGPZML","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1907.04214","citing_title":"Entropic Regularization of Markov Decision Processes","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22507","citing_title":"Generative Modeling by Value-Driven Transport","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22622","citing_title":"A note on convergence of Wasserstein policy optimization","ref_index":100,"is_internal_anchor":true},{"citing_arxiv_id":"2506.00286","citing_title":"Recursive Entropic Risk Optimization in Discounted MDPs: Sample Complexity Bounds with a Generative Model","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15651","citing_title":"Sharp Spectral Thresholds for Logit Fixed Points","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18591","citing_title":"Randomized Advantage Transformation (RAT): Computing Natural Policy Gradients via Direct Backpropagation","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2512.23927","citing_title":"Stationary Reweighting Yields Local Convergence of Soft Fitted Q-Iteration","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11020","citing_title":"Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08946","citing_title":"A Single Deep Preference-Conditioned Policy for Learning Pareto Coverage Sets","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09214","citing_title":"Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07775","citing_title":"POETS: Uncertainty-Aware LLM Optimization via Compute-Efficient Policy Ensembles","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17415","citing_title":"Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19695","citing_title":"Planning in entropy-regularized Markov decision processes and games","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI","json":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI.json","graph_json":"https://pith.science/api/pith-number/5SHGPZMLNH7YKDKIHNGMGI6KHI/graph.json","events_json":"https://pith.science/api/pith-number/5SHGPZMLNH7YKDKIHNGMGI6KHI/events.json","paper":"https://pith.science/paper/5SHGPZML"},"agent_actions":{"view_html":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI","download_json":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI.json","view_paper":"https://pith.science/paper/5SHGPZML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.07798&json=true","fetch_graph":"https://pith.science/api/pith-number/5SHGPZMLNH7YKDKIHNGMGI6KHI/graph.json","fetch_events":"https://pith.science/api/pith-number/5SHGPZMLNH7YKDKIHNGMGI6KHI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/action/storage_attestation","attest_author":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/action/author_attestation","sign_citation":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/action/citation_signature","submit_replication":"https://pith.science/pith/5SHGPZMLNH7YKDKIHNGMGI6KHI/action/replication_record"}},"created_at":"2026-05-18T00:44:04.536701+00:00","updated_at":"2026-05-18T00:44:04.536701+00:00"}