{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:DKREUUR6KM7OB22JL2S7KLQAPI","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":"ecbb6b1efcbeb6ef31dfc0f75d3dc61a18bfaaf2351787b17758d35f61cc3fc3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:38:47Z","title_canon_sha256":"d3db49106b23606ca82e4a74cbf86ba342f17b44d61f5c0f4d5fedb3452fd071"},"schema_version":"1.0","source":{"id":"1511.06295","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06295","created_at":"2026-05-18T01:23:12Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06295v2","created_at":"2026-05-18T01:23:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06295","created_at":"2026-05-18T01:23:12Z"},{"alias_kind":"pith_short_12","alias_value":"DKREUUR6KM7O","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_16","alias_value":"DKREUUR6KM7OB22J","created_at":"2026-05-18T12:29:17Z"},{"alias_kind":"pith_short_8","alias_value":"DKREUUR6","created_at":"2026-05-18T12:29:17Z"}],"graph_snapshots":[{"event_id":"sha256:b9eb099135408cfc46da701d3c1aec84b213131b765c60ecc62145fa71743d56","target":"graph","created_at":"2026-05-18T01:23:12Z","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":"Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance. In this work, we present a novel method called policy distillation that can be used to extract the policy of a reinforcement learning agent and train a new network that performs at the expert level while being dramatically smaller and more efficient. Furthermore, the same method can be used to consolidate multiple task-specific policies into ","authors_text":"Andrei A. Rusu, Caglar Gulcehre, Guillaume Desjardins, James Kirkpatrick, Koray Kavukcuoglu, Raia Hadsell, Razvan Pascanu, Sergio Gomez Colmenarejo, Volodymyr Mnih","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:38:47Z","title":"Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06295","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:ebf1fdef355ea1e8507b5fb7ada34c3aac6f3f485ac96fe8fe40573db48ba38d","target":"record","created_at":"2026-05-18T01:23:12Z","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":"ecbb6b1efcbeb6ef31dfc0f75d3dc61a18bfaaf2351787b17758d35f61cc3fc3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:38:47Z","title_canon_sha256":"d3db49106b23606ca82e4a74cbf86ba342f17b44d61f5c0f4d5fedb3452fd071"},"schema_version":"1.0","source":{"id":"1511.06295","kind":"arxiv","version":2}},"canonical_sha256":"1aa24a523e533ee0eb495ea5f52e007a09f9e005c3a3940c108ca5933da3f641","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1aa24a523e533ee0eb495ea5f52e007a09f9e005c3a3940c108ca5933da3f641","first_computed_at":"2026-05-18T01:23:12.982188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:23:12.982188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HGZUykh7ZwbXTHYXAYzNehyqOPNu7vaqgMLa2JRTuy0fVHhuzqUMrSf2+vQAS4B+4pX7gjY5Jmyw/gcuJMkUDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:23:12.982881Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06295","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebf1fdef355ea1e8507b5fb7ada34c3aac6f3f485ac96fe8fe40573db48ba38d","sha256:b9eb099135408cfc46da701d3c1aec84b213131b765c60ecc62145fa71743d56"],"state_sha256":"387d29fbaf8b397e22fc1567099c70f4343c81db12c11f07351dd4acc44d0814"}