{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PQXFOVOLPUHXGR42IKOM75MT7Z","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":"3f0ae132ec13b5f3194224582cf6416e59add7a20cc7aa7ffa2aa17b338c2a92","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T18:04:19Z","title_canon_sha256":"079649260771c1704657dd81bcb76f4a53f6fb7128809fb409714971e69f19a3"},"schema_version":"1.0","source":{"id":"2106.00707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00707","created_at":"2026-07-05T02:45:39Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00707v1","created_at":"2026-07-05T02:45:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00707","created_at":"2026-07-05T02:45:39Z"},{"alias_kind":"pith_short_12","alias_value":"PQXFOVOLPUHX","created_at":"2026-07-05T02:45:39Z"},{"alias_kind":"pith_short_16","alias_value":"PQXFOVOLPUHXGR42","created_at":"2026-07-05T02:45:39Z"},{"alias_kind":"pith_short_8","alias_value":"PQXFOVOL","created_at":"2026-07-05T02:45:39Z"}],"graph_snapshots":[{"event_id":"sha256:cb079e37c7be1ab63884fd3680b6c14e8c473e2b372e3e28065c37bac462a9e3","target":"graph","created_at":"2026-07-05T02:45:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.00707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy-based reinforcement learning methods suffer from the policy collapse problem. We find valued-based reinforcement learning methods with {\\epsilon}-greedy mechanism are capable of enjoying three characteristics, Closed-form Diversity, Objective-invariant Exploration and Adaptive Trade-off, which help value-based methods avoid the policy collapse problem. However, there does not exist a parallel mechanism for policy-based methods that achieves all three characteristics. In this paper, we propose an entropy regularization free mechanism that is designed for policy-based methods, which achie","authors_text":"Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T18:04:19Z","title":"An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00707","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":"sha256:05a3f5a4ee94f1d8c8971d5261d586b19efb053fbaea5fde361fe3d716a8a95e","target":"record","created_at":"2026-07-05T02:45:39Z","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":"3f0ae132ec13b5f3194224582cf6416e59add7a20cc7aa7ffa2aa17b338c2a92","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-01T18:04:19Z","title_canon_sha256":"079649260771c1704657dd81bcb76f4a53f6fb7128809fb409714971e69f19a3"},"schema_version":"1.0","source":{"id":"2106.00707","kind":"arxiv","version":1}},"canonical_sha256":"7c2e5755cb7d0f73479a429ccff593fe77bf888a1ef48ecaed8716a7eeb4350b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c2e5755cb7d0f73479a429ccff593fe77bf888a1ef48ecaed8716a7eeb4350b","first_computed_at":"2026-07-05T02:45:39.202562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:45:39.202562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a7rMZ0+DtxEVY/9/BiJBJzZsKYbywgvV2SD81+CcoyLQtiWhsQ6iyLdoj+8c4Fc9bmOSmFbkkjiF6JSQBM3WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:45:39.202961Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05a3f5a4ee94f1d8c8971d5261d586b19efb053fbaea5fde361fe3d716a8a95e","sha256:cb079e37c7be1ab63884fd3680b6c14e8c473e2b372e3e28065c37bac462a9e3"],"state_sha256":"0433f9725690c56930b331ad819fbe2efeac1fde89ac8e9a956e1fea6f5aa770"}