{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LXW7ADRAFZ5QJVXTK4GUVW5V4F","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":"860df1214d29c6da11ecd3a7d2a29038732841aaaab7492e8190f0379da633aa","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T15:44:41Z","title_canon_sha256":"5057549b392403e04934b18a29817b51846efb3b51f3f444fb1679c0ba171282"},"schema_version":"1.0","source":{"id":"1906.09205","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09205","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09205v1","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09205","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"LXW7ADRAFZ5Q","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LXW7ADRAFZ5QJVXT","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LXW7ADRA","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:44eac16c8a63978eba5b9d2b29512fda9ac46088054d7044ff66efcfc39d6ad5","target":"graph","created_at":"2026-05-17T23:42:44Z","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":"Deep reinforcement learning has made significant progress in the field of continuous control, such as physical control and autonomous driving. However, it is challenging for a reinforcement model to learn a policy for each task sequentially due to catastrophic forgetting. Specifically, the model would forget knowledge it learned in the past when trained on a new task. We consider this challenge from two perspectives: i) acquiring task-specific skills is difficult since task information and rewards are not highly related; ii) learning knowledge from previous experience is difficult in continuou","authors_text":"Fengda Zhu, Mingkui Tan, Runhao Zeng, Xiaojun Chang","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T15:44:41Z","title":"Continual Reinforcement Learning with Diversity Exploration and Adversarial Self-Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09205","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":"sha256:81f4d9a32227793f77ba32089063ee3ed0a09b51641760f2c51a51bcde0482a1","target":"record","created_at":"2026-05-17T23:42:44Z","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":"860df1214d29c6da11ecd3a7d2a29038732841aaaab7492e8190f0379da633aa","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T15:44:41Z","title_canon_sha256":"5057549b392403e04934b18a29817b51846efb3b51f3f444fb1679c0ba171282"},"schema_version":"1.0","source":{"id":"1906.09205","kind":"arxiv","version":1}},"canonical_sha256":"5dedf00e202e7b04d6f3570d4adbb5e16e5fee4ed02bf380d9521c0e0895a69a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5dedf00e202e7b04d6f3570d4adbb5e16e5fee4ed02bf380d9521c0e0895a69a","first_computed_at":"2026-05-17T23:42:44.172267Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:44.172267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KQXKcgWcfHfz37N2e2oOIM8RKJlyDrnbNxR32YGyVATepEF3jPj2B58INf3rhrq3z7VdnH1oOpi+83gpN+xVDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:44.172942Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09205","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81f4d9a32227793f77ba32089063ee3ed0a09b51641760f2c51a51bcde0482a1","sha256:44eac16c8a63978eba5b9d2b29512fda9ac46088054d7044ff66efcfc39d6ad5"],"state_sha256":"e80b236b643abcce8d2f30ea549656e8890e1348f663fb27092d41ea1fa55769"}