{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:F2WRGIULRQBYJWI7IFQ355MYM6","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":"928e9db8dc0987c9adebcea0ef202d9414a3e37a3e28098e3855bfd2277e2bcc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-29T11:10:37Z","title_canon_sha256":"06dced55974968644d1137d9e993e6c159d82b7be20a3953b94cae3a65170ac4"},"schema_version":"1.0","source":{"id":"1912.12630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.12630","created_at":"2026-07-05T00:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"1912.12630v1","created_at":"2026-07-05T00:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.12630","created_at":"2026-07-05T00:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"F2WRGIULRQBY","created_at":"2026-07-05T00:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"F2WRGIULRQBYJWI7","created_at":"2026-07-05T00:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"F2WRGIUL","created_at":"2026-07-05T00:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:a7033de9fa42821f9e2b0d832a1943c438108ecbbce17e2d3ca226b4658afbaa","target":"graph","created_at":"2026-07-05T00:29:02Z","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/1912.12630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy distillation in deep reinforcement learning provides an effective way to transfer control policies from a larger network to a smaller untrained network without a significant degradation in performance. However, policy distillation is underexplored in deep reinforcement learning, and existing approaches are computationally inefficient, resulting in a long distillation time. In addition, the effectiveness of the distillation process is still limited to the model capacity. We propose a new distillation mechanism, called real-time policy distillation, in which training the teacher model and","authors_text":"Pooyan Fazli, Yuxiang Sun","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-29T11:10:37Z","title":"Real-time Policy Distillation in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.12630","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:d51ae1d983f33ff3475b8221cb510c0ec3d28f8cb64c236441e86561663062cf","target":"record","created_at":"2026-07-05T00:29:02Z","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":"928e9db8dc0987c9adebcea0ef202d9414a3e37a3e28098e3855bfd2277e2bcc","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-29T11:10:37Z","title_canon_sha256":"06dced55974968644d1137d9e993e6c159d82b7be20a3953b94cae3a65170ac4"},"schema_version":"1.0","source":{"id":"1912.12630","kind":"arxiv","version":1}},"canonical_sha256":"2ead13228b8c0384d91f4161bef59867865209bcdbd0b8723881614bca5ec5ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ead13228b8c0384d91f4161bef59867865209bcdbd0b8723881614bca5ec5ba","first_computed_at":"2026-07-05T00:29:02.023854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:29:02.023854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WHAN2NVdJclNqOgFx2kSghTgaCIAaCXdBcsOYDYCXr1T+xQES/8mk68UXNO+arT0OquRw89ZdoDs7T1o/zNMBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:29:02.024190Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.12630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d51ae1d983f33ff3475b8221cb510c0ec3d28f8cb64c236441e86561663062cf","sha256:a7033de9fa42821f9e2b0d832a1943c438108ecbbce17e2d3ca226b4658afbaa"],"state_sha256":"67c404e2b3cca343bf499f72603035102f0188a50f38ae37174ee47205d10f75"}