{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CS3DV2TCJ33JF4PQYVXQ5TRWZF","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":"ad2fd6aaa1ecf6c55ab6d2e1bb3d6ee4379b9133b51f7e780309c60b91341973","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T09:49:18Z","title_canon_sha256":"6a1ce0243603157d7d288063603dff3484a3e3e7b734512f456d6bc7fc3cef57"},"schema_version":"1.0","source":{"id":"1809.01906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01906","created_at":"2026-05-18T00:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01906v2","created_at":"2026-05-18T00:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01906","created_at":"2026-05-18T00:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"CS3DV2TCJ33J","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CS3DV2TCJ33JF4PQ","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CS3DV2TC","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:6418479cbac50e2b6a1fb5edf238f93d35c2bf329284bddb7c8c02ea5d86d9a8","target":"graph","created_at":"2026-05-18T00:00:18Z","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"},"paper":{"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 ","authors_text":"Felix Leibfried, Peter Vrancx","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T09:49:18Z","title":"Model-Based Regularization for Deep Reinforcement Learning with Transcoder Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01906","kind":"arxiv","version":2},"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":"sha256:2caafbda626ea40307555283c614ab8a8fd30cc92b7335bdcda105206fd22e90","target":"record","created_at":"2026-05-18T00:00:18Z","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":"ad2fd6aaa1ecf6c55ab6d2e1bb3d6ee4379b9133b51f7e780309c60b91341973","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-06T09:49:18Z","title_canon_sha256":"6a1ce0243603157d7d288063603dff3484a3e3e7b734512f456d6bc7fc3cef57"},"schema_version":"1.0","source":{"id":"1809.01906","kind":"arxiv","version":2}},"canonical_sha256":"14b63aea624ef692f1f0c56f0ece36c97d5b91495a2af333f8082ee4f00010bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14b63aea624ef692f1f0c56f0ece36c97d5b91495a2af333f8082ee4f00010bc","first_computed_at":"2026-05-18T00:00:18.171772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:18.171772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QkNjD80nKXmBvtMhnVbxTuAcRIyumVT0m+RDPpODXjJBCbOSxLFis0oOf0YVWZUGTWP6fanmnJRFSJlYHnLGDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:18.172351Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2caafbda626ea40307555283c614ab8a8fd30cc92b7335bdcda105206fd22e90","sha256:6418479cbac50e2b6a1fb5edf238f93d35c2bf329284bddb7c8c02ea5d86d9a8"],"state_sha256":"120ccf8dd89c68ea05b518e34f3f0fc528f4cad27c7d54c91a68dee8305847c3"}