{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XVE3NROPIZ7PV45TYO3FM57UR3","short_pith_number":"pith:XVE3NROP","schema_version":"1.0","canonical_sha256":"bd49b6c5cf467efaf3b3c3b65677f48ee78fbef6966c5e3a48ca75f99accae16","source":{"kind":"arxiv","id":"1807.00737","version":5},"attestation_state":"computed","paper":{"title":"Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Zhao, Volker Tresp","submitted_at":"2018-07-02T15:14:43Z","abstract_excerpt":"Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and"},"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":"1807.00737","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T15:14:43Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"aba203a93fd06ced65b93b874a2fff9bf71a46fbe6e132e8ea80d61156ffd0be","abstract_canon_sha256":"211c477b0bded4715345c39d33c79c2e14df3ce68061f05b5cf695187503cb99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:05:08.169923Z","signature_b64":"EYyosGtXPW2YON07oucOQCsUcB4hQzdZptfW+Ngh/sM+ZAc+dXVZmzs5xRpLNZIIXMyvkhifk8L5bFIT319hCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd49b6c5cf467efaf3b3c3b65677f48ee78fbef6966c5e3a48ca75f99accae16","last_reissued_at":"2026-07-05T01:05:08.169557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:05:08.169557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Goal-Oriented Visual Dialog via Tempered Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Rui Zhao, Volker Tresp","submitted_at":"2018-07-02T15:14:43Z","abstract_excerpt":"Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extensions for policy gradient methods, which are referred to as Tempered Policy Gradients (TPGs). On a recent AI-testbed, i.e., the GuessWhat?! game, we achieve significant improvements with two innovations. The first one is an extension of the state-of-the-art solutions with Seq2Seq and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00737","kind":"arxiv","version":5},"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/1807.00737/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":"1807.00737","created_at":"2026-07-05T01:05:08.169614+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00737v5","created_at":"2026-07-05T01:05:08.169614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00737","created_at":"2026-07-05T01:05:08.169614+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVE3NROPIZ7P","created_at":"2026-07-05T01:05:08.169614+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVE3NROPIZ7PV45T","created_at":"2026-07-05T01:05:08.169614+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVE3NROP","created_at":"2026-07-05T01:05:08.169614+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/XVE3NROPIZ7PV45TYO3FM57UR3","json":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3.json","graph_json":"https://pith.science/api/pith-number/XVE3NROPIZ7PV45TYO3FM57UR3/graph.json","events_json":"https://pith.science/api/pith-number/XVE3NROPIZ7PV45TYO3FM57UR3/events.json","paper":"https://pith.science/paper/XVE3NROP"},"agent_actions":{"view_html":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3","download_json":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3.json","view_paper":"https://pith.science/paper/XVE3NROP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00737&json=true","fetch_graph":"https://pith.science/api/pith-number/XVE3NROPIZ7PV45TYO3FM57UR3/graph.json","fetch_events":"https://pith.science/api/pith-number/XVE3NROPIZ7PV45TYO3FM57UR3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3/action/storage_attestation","attest_author":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3/action/author_attestation","sign_citation":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3/action/citation_signature","submit_replication":"https://pith.science/pith/XVE3NROPIZ7PV45TYO3FM57UR3/action/replication_record"}},"created_at":"2026-07-05T01:05:08.169614+00:00","updated_at":"2026-07-05T01:05:08.169614+00:00"}