{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SDOJW5VYH24SUI6XP3X76AW3EY","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":"803ba1eb8935e36a15fccf2783263fe1ea305068ba7623274d204251ac394e7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T16:15:13Z","title_canon_sha256":"361813252bffb38095ec008887389971cec37806f0a0efdd42250de4149bcba7"},"schema_version":"1.0","source":{"id":"2112.03798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03798","created_at":"2026-07-05T03:39:05Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03798v2","created_at":"2026-07-05T03:39:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03798","created_at":"2026-07-05T03:39:05Z"},{"alias_kind":"pith_short_12","alias_value":"SDOJW5VYH24S","created_at":"2026-07-05T03:39:05Z"},{"alias_kind":"pith_short_16","alias_value":"SDOJW5VYH24SUI6X","created_at":"2026-07-05T03:39:05Z"},{"alias_kind":"pith_short_8","alias_value":"SDOJW5VY","created_at":"2026-07-05T03:39:05Z"}],"graph_snapshots":[{"event_id":"sha256:5e4bc80216a662f62b7cb6c9113cb16bc620273f135695dd480afda21819d210","target":"graph","created_at":"2026-07-05T03:39:05Z","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/2112.03798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"On-policy deep reinforcement learning algorithms have low data utilization and require significant experience for policy improvement. This paper proposes a proximal policy optimization algorithm with prioritized trajectory replay (PTR-PPO) that combines on-policy and off-policy methods to improve sampling efficiency by prioritizing the replay of trajectories generated by old policies. We first design three trajectory priorities based on the characteristics of trajectories: the first two being max and mean trajectory priorities based on one-step empirical generalized advantage estimation (GAE) ","authors_text":"Xingxing Liang, Yanghe Feng, Yang Ma, Zhong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T16:15:13Z","title":"PTR-PPO: Proximal Policy Optimization with Prioritized Trajectory Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03798","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":"sha256:44ff3d5481950fc69df3d730330ce4d189fb551ddf6b5404a558c1395ef7eb4d","target":"record","created_at":"2026-07-05T03:39:05Z","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":"803ba1eb8935e36a15fccf2783263fe1ea305068ba7623274d204251ac394e7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-07T16:15:13Z","title_canon_sha256":"361813252bffb38095ec008887389971cec37806f0a0efdd42250de4149bcba7"},"schema_version":"1.0","source":{"id":"2112.03798","kind":"arxiv","version":2}},"canonical_sha256":"90dc9b76b83eb92a23d77eefff02db2616a91325daea382da450ae799194d6ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90dc9b76b83eb92a23d77eefff02db2616a91325daea382da450ae799194d6ee","first_computed_at":"2026-07-05T03:39:05.062654Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:39:05.062654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gCILkWSB86TzdP4iW+FKJA0wJJqBZlu4FwKwA2ahU5tYlTBJd9e47LtAf/eKVhVlT9RW8NDJrQ/b3OaLpcUBDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:39:05.063130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44ff3d5481950fc69df3d730330ce4d189fb551ddf6b5404a558c1395ef7eb4d","sha256:5e4bc80216a662f62b7cb6c9113cb16bc620273f135695dd480afda21819d210"],"state_sha256":"963eff60c0dba50b608292e2bf178ec40cd431c1856d7710bbb369c5e27febc8"}