{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5B6S4YADNQ44WZUEINNVEVMSBR","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":"1362b175b302fd576bdef77556b555a126ce12460088105078800f651f2b2724","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-02T06:25:19Z","title_canon_sha256":"dedb0f24327785c307a6b4c8f41dc704e48ee28c22fefea48c8a2b2563bd82cf"},"schema_version":"1.0","source":{"id":"1806.00589","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.00589","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"arxiv_version","alias_value":"1806.00589v1","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00589","created_at":"2026-05-18T00:14:18Z"},{"alias_kind":"pith_short_12","alias_value":"5B6S4YADNQ44","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5B6S4YADNQ44WZUE","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5B6S4YAD","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:a0882541a43a95ed2e8259d8d76571060233db180218be9d120fdf9113c791bc","target":"graph","created_at":"2026-05-18T00:14:18Z","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":"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","authors_text":"Keith W. Ross, Kenny Song, Quan Ho Vuong, Xiao-Yue Gong, Yiming Zhang","cross_cats":["cs.AI","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-02T06:25:19Z","title":"Efficient Entropy for Policy Gradient with Multidimensional Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00589","kind":"arxiv","version":1},"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":"sha256:436dea94a00b113e28d4cd0e2a683e8d9e101f0b93308fd4b7519703f6ca2040","target":"record","created_at":"2026-05-18T00:14:18Z","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":"1362b175b302fd576bdef77556b555a126ce12460088105078800f651f2b2724","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-02T06:25:19Z","title_canon_sha256":"dedb0f24327785c307a6b4c8f41dc704e48ee28c22fefea48c8a2b2563bd82cf"},"schema_version":"1.0","source":{"id":"1806.00589","kind":"arxiv","version":1}},"canonical_sha256":"e87d2e60036c39cb6684435b5255920c783e40eac7072a12658cf44bb39c9011","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e87d2e60036c39cb6684435b5255920c783e40eac7072a12658cf44bb39c9011","first_computed_at":"2026-05-18T00:14:18.994938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:18.994938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dun77k626QOo0qofADdXh/BSwL/7kENmdzNxQ2tg+k8g/EjTwGMti8aCp/YZrQAINT5u03syN7809NlrwG5XDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:18.995381Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.00589","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:436dea94a00b113e28d4cd0e2a683e8d9e101f0b93308fd4b7519703f6ca2040","sha256:a0882541a43a95ed2e8259d8d76571060233db180218be9d120fdf9113c791bc"],"state_sha256":"dea5a14be871c9d3369f3c299b8bbb40df22257927f70c8d5e0866e30b0e2b4d"}