{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CS3DV2TCJ33JF4PQYVXQ5TRWZF","short_pith_number":"pith:CS3DV2TC","schema_version":"1.0","canonical_sha256":"14b63aea624ef692f1f0c56f0ece36c97d5b91495a2af333f8082ee4f00010bc","source":{"kind":"arxiv","id":"1809.01906","version":2},"attestation_state":"computed","paper":{"title":"Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Leibfried, Peter Vrancx","submitted_at":"2018-09-06T09:49:18Z","abstract_excerpt":"This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the model are included in the basic DQN loss as additional regularizers. This augmented objective leads to a richer training signal that provides feedback at every time step. Moreover, because learning an environment model shares a common structure with the RL problem, we hypothesize that the resulting objective improves both sample efficiency and performance. We "},"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":"1809.01906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T09:49:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6a1ce0243603157d7d288063603dff3484a3e3e7b734512f456d6bc7fc3cef57","abstract_canon_sha256":"ad2fd6aaa1ecf6c55ab6d2e1bb3d6ee4379b9133b51f7e780309c60b91341973"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:18.172351Z","signature_b64":"QkNjD80nKXmBvtMhnVbxTuAcRIyumVT0m+RDPpODXjJBCbOSxLFis0oOf0YVWZUGTWP6fanmnJRFSJlYHnLGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14b63aea624ef692f1f0c56f0ece36c97d5b91495a2af333f8082ee4f00010bc","last_reissued_at":"2026-05-18T00:00:18.171772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:18.171772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Leibfried, Peter Vrancx","submitted_at":"2018-09-06T09:49:18Z","abstract_excerpt":"This paper proposes a new optimization objective for value-based deep reinforcement learning. We extend conventional Deep Q-Networks (DQNs) by adding a model-learning component yielding a transcoder network. The prediction errors for the model are included in the basic DQN loss as additional regularizers. This augmented objective leads to a richer training signal that provides feedback at every time step. Moreover, because learning an environment model shares a common structure with the RL problem, we hypothesize that the resulting objective improves both sample efficiency and performance. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01906","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":""},"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":"1809.01906","created_at":"2026-05-18T00:00:18.171856+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01906v2","created_at":"2026-05-18T00:00:18.171856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01906","created_at":"2026-05-18T00:00:18.171856+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS3DV2TCJ33J","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS3DV2TCJ33JF4PQ","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS3DV2TC","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF","json":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF.json","graph_json":"https://pith.science/api/pith-number/CS3DV2TCJ33JF4PQYVXQ5TRWZF/graph.json","events_json":"https://pith.science/api/pith-number/CS3DV2TCJ33JF4PQYVXQ5TRWZF/events.json","paper":"https://pith.science/paper/CS3DV2TC"},"agent_actions":{"view_html":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF","download_json":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF.json","view_paper":"https://pith.science/paper/CS3DV2TC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01906&json=true","fetch_graph":"https://pith.science/api/pith-number/CS3DV2TCJ33JF4PQYVXQ5TRWZF/graph.json","fetch_events":"https://pith.science/api/pith-number/CS3DV2TCJ33JF4PQYVXQ5TRWZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF/action/storage_attestation","attest_author":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF/action/author_attestation","sign_citation":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF/action/citation_signature","submit_replication":"https://pith.science/pith/CS3DV2TCJ33JF4PQYVXQ5TRWZF/action/replication_record"}},"created_at":"2026-05-18T00:00:18.171856+00:00","updated_at":"2026-05-18T00:00:18.171856+00:00"}