{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PPZQ3XFU4YK536VBV7JLBQX5VA","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":"cd6edb21a9ae499b45672a5d624f174422555f4123aff9f5c1f8572010e13d49","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-09T13:05:47Z","title_canon_sha256":"e4899f4f6dad38f47f139b14ca1b3aa566209cb5a4f01fdfe2e5f4ee3c9fea01"},"schema_version":"1.0","source":{"id":"2003.04108","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.04108","created_at":"2026-07-05T01:11:34Z"},{"alias_kind":"arxiv_version","alias_value":"2003.04108v2","created_at":"2026-07-05T01:11:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.04108","created_at":"2026-07-05T01:11:34Z"},{"alias_kind":"pith_short_12","alias_value":"PPZQ3XFU4YK5","created_at":"2026-07-05T01:11:34Z"},{"alias_kind":"pith_short_16","alias_value":"PPZQ3XFU4YK536VB","created_at":"2026-07-05T01:11:34Z"},{"alias_kind":"pith_short_8","alias_value":"PPZQ3XFU","created_at":"2026-07-05T01:11:34Z"}],"graph_snapshots":[{"event_id":"sha256:71c0b342a81dd8c51c7835b1f4c45aee54bb4447941ed3e7da0662bd83d10507","target":"graph","created_at":"2026-07-05T01:11:34Z","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/2003.04108/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO) are among the most successful policy gradient approaches in deep reinforcement learning (RL). While these methods achieve state-of-the-art performance across a wide range of challenging tasks, there is room for improvement in the stabilization of the policy learning and how the off-policy data are used. In this paper we revisit the theoretical foundations of these algorithms and propose a new algorithm which stabilizes the policy improvement through a proximity term that constrains the discounted state-action visita","authors_text":"Ahmed Touati, Amy Zhang, Joelle Pineau, Pascal Vincent","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-09T13:05:47Z","title":"Stable Policy Optimization via Off-Policy Divergence Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.04108","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":"sha256:2bb07c7391b866c99cec40374dd376e386097afb8601bf81c2d240225842c17d","target":"record","created_at":"2026-07-05T01:11:34Z","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":"cd6edb21a9ae499b45672a5d624f174422555f4123aff9f5c1f8572010e13d49","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-09T13:05:47Z","title_canon_sha256":"e4899f4f6dad38f47f139b14ca1b3aa566209cb5a4f01fdfe2e5f4ee3c9fea01"},"schema_version":"1.0","source":{"id":"2003.04108","kind":"arxiv","version":2}},"canonical_sha256":"7bf30ddcb4e615ddfaa1afd2b0c2fda8313ecd958c95551c3aa66c7f364c0ead","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bf30ddcb4e615ddfaa1afd2b0c2fda8313ecd958c95551c3aa66c7f364c0ead","first_computed_at":"2026-07-05T01:11:34.120666Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:34.120666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZDL/z9O9ogkFipK2PqgHsXeKgGwD/V+p0WHDS/f+/TqGcugxJcRPGUaknpjTYXIg8GSHK63HlRRoTvsBSLdiCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:34.121102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.04108","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2bb07c7391b866c99cec40374dd376e386097afb8601bf81c2d240225842c17d","sha256:71c0b342a81dd8c51c7835b1f4c45aee54bb4447941ed3e7da0662bd83d10507"],"state_sha256":"cd99412480498a14b21cfce1ca3991340200ef60d0caf5d47704a07be75c7cc6"}