{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5B6S4YADNQ44WZUEINNVEVMSBR","short_pith_number":"pith:5B6S4YAD","schema_version":"1.0","canonical_sha256":"e87d2e60036c39cb6684435b5255920c783e40eac7072a12658cf44bb39c9011","source":{"kind":"arxiv","id":"1806.00589","version":1},"attestation_state":"computed","paper":{"title":"Efficient Entropy for Policy Gradient with Multidimensional Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keith W. Ross, Kenny Song, Quan Ho Vuong, Xiao-Yue Gong, Yiming Zhang","submitted_at":"2018-06-02T06:25:19Z","abstract_excerpt":"In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This paper considers entropy bonus, which is used to encourage exploration in policy gradient. In the case of high-dimensional action spaces, calculating the entropy and its gradient requires enumerating all the actions in the action space and running forward and backpropagation for eac"},"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":"1806.00589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-02T06:25:19Z","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"title_canon_sha256":"dedb0f24327785c307a6b4c8f41dc704e48ee28c22fefea48c8a2b2563bd82cf","abstract_canon_sha256":"1362b175b302fd576bdef77556b555a126ce12460088105078800f651f2b2724"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:18.995381Z","signature_b64":"dun77k626QOo0qofADdXh/BSwL/7kENmdzNxQ2tg+k8g/EjTwGMti8aCp/YZrQAINT5u03syN7809NlrwG5XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e87d2e60036c39cb6684435b5255920c783e40eac7072a12658cf44bb39c9011","last_reissued_at":"2026-05-18T00:14:18.994938Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:18.994938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Entropy for Policy Gradient with Multidimensional Action Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Keith W. Ross, Kenny Song, Quan Ho Vuong, Xiao-Yue Gong, Yiming Zhang","submitted_at":"2018-06-02T06:25:19Z","abstract_excerpt":"In recent years, deep reinforcement learning has been shown to be adept at solving sequential decision processes with high-dimensional state spaces such as in the Atari games. Many reinforcement learning problems, however, involve high-dimensional discrete action spaces as well as high-dimensional state spaces. This paper considers entropy bonus, which is used to encourage exploration in policy gradient. In the case of high-dimensional action spaces, calculating the entropy and its gradient requires enumerating all the actions in the action space and running forward and backpropagation for eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00589","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":"1806.00589","created_at":"2026-05-18T00:14:18.995004+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00589v1","created_at":"2026-05-18T00:14:18.995004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00589","created_at":"2026-05-18T00:14:18.995004+00:00"},{"alias_kind":"pith_short_12","alias_value":"5B6S4YADNQ44","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5B6S4YADNQ44WZUE","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5B6S4YAD","created_at":"2026-05-18T12:32:08.215937+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/5B6S4YADNQ44WZUEINNVEVMSBR","json":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR.json","graph_json":"https://pith.science/api/pith-number/5B6S4YADNQ44WZUEINNVEVMSBR/graph.json","events_json":"https://pith.science/api/pith-number/5B6S4YADNQ44WZUEINNVEVMSBR/events.json","paper":"https://pith.science/paper/5B6S4YAD"},"agent_actions":{"view_html":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR","download_json":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR.json","view_paper":"https://pith.science/paper/5B6S4YAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00589&json=true","fetch_graph":"https://pith.science/api/pith-number/5B6S4YADNQ44WZUEINNVEVMSBR/graph.json","fetch_events":"https://pith.science/api/pith-number/5B6S4YADNQ44WZUEINNVEVMSBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR/action/storage_attestation","attest_author":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR/action/author_attestation","sign_citation":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR/action/citation_signature","submit_replication":"https://pith.science/pith/5B6S4YADNQ44WZUEINNVEVMSBR/action/replication_record"}},"created_at":"2026-05-18T00:14:18.995004+00:00","updated_at":"2026-05-18T00:14:18.995004+00:00"}