{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HTYLDZNQRRZELXNQRGXV4A6XVE","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":"196a71a5eb4fe82975cbddf182cb32a0a6b272662ef0a22184b5dacbc9cc9751","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T00:01:29Z","title_canon_sha256":"57014655e767efa13a1734b880571b9f111dfc7bfdb91918eddb176eb241711d"},"schema_version":"1.0","source":{"id":"2405.16383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16383","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16383v1","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16383","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"HTYLDZNQRRZE","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"HTYLDZNQRRZELXNQ","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"HTYLDZNQ","created_at":"2026-07-05T08:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:332d8c3156ba14b3e7ecdb00fdb26bc55db78732305cd07c0ad0a2b6e5344b47","target":"graph","created_at":"2026-07-05T08:23:29Z","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/2405.16383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a new on-policy algorithm called Rewarded Region Replay (R3), which significantly improves on PPO in solving environments with discrete action spaces. R3 improves sample efficiency by using a replay buffer which contains past successful trajectories with reward above a certain threshold, which are used to update a PPO agent with importance sampling. Crucially, we discard the importance sampling factors which are above a certain ratio to reduce variance and stabilize training. We found that R3 significantly outperforms PPO in Minigrid environments with sparse rewards and discrete a","authors_text":"Bangzheng Li, Ningshan Ma, Zifan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T00:01:29Z","title":"Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16383","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:f7048a1d20dd34a67a14a2ac39588767a06250cd942a37cb691744faf9b1e6fc","target":"record","created_at":"2026-07-05T08:23:29Z","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":"196a71a5eb4fe82975cbddf182cb32a0a6b272662ef0a22184b5dacbc9cc9751","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-26T00:01:29Z","title_canon_sha256":"57014655e767efa13a1734b880571b9f111dfc7bfdb91918eddb176eb241711d"},"schema_version":"1.0","source":{"id":"2405.16383","kind":"arxiv","version":1}},"canonical_sha256":"3cf0b1e5b08c7245ddb089af5e03d7a93a2513799afc4441eb2d769805c00ad4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf0b1e5b08c7245ddb089af5e03d7a93a2513799afc4441eb2d769805c00ad4","first_computed_at":"2026-07-05T08:23:29.399904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:29.399904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vaei7NnAvJw/dmFuDVJYXUCFb+ejhNjjPiy4Mjw2NJGXBcD8ccfdZrloXidTPzfpihDlzmDYvM+C/+u2QBY4Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:29.400365Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7048a1d20dd34a67a14a2ac39588767a06250cd942a37cb691744faf9b1e6fc","sha256:332d8c3156ba14b3e7ecdb00fdb26bc55db78732305cd07c0ad0a2b6e5344b47"],"state_sha256":"52211b035e50e93776244674a704bb51f70cd9611ca0ebc714ef862d43732d8e"}