{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ROSHO2DYCX7OJULRVJWA27V3OS","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":"1e68451927de3db4955a9e3d5f529f2971a3e8b683774738d402d57ad0528513","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T01:32:02Z","title_canon_sha256":"ee3d769f0746033feebfb4174de7b0d3bbb86feae03da8434e8d89f3b8307d72"},"schema_version":"1.0","source":{"id":"1812.02868","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02868","created_at":"2026-05-17T23:58:35Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02868v2","created_at":"2026-05-17T23:58:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02868","created_at":"2026-05-17T23:58:35Z"},{"alias_kind":"pith_short_12","alias_value":"ROSHO2DYCX7O","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ROSHO2DYCX7OJULR","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ROSHO2DY","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:2e7e540f4b192593247659206d72e8f3e252c3bbafdbad0904a2997bb283e448","target":"graph","created_at":"2026-05-17T23:58:35Z","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 methods have achieved remarkable performance on challenging control tasks. Observations of the resulting behavior give the impression that the agent has constructed a generalized representation that supports insightful action decisions. We re-examine what is meant by generalization in RL, and propose several definitions based on an agent's performance in on-policy, off-policy, and unreachable states. We propose a set of practical methods for evaluating agents with these definitions of generalization. We demonstrate these techniques on a common benchmark task for dee","authors_text":"Akanksha Atrey, David Jensen, Emma Tosch, Jun Ki Lee, Michael Littman, Sam Witty","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T01:32:02Z","title":"Measuring and Characterizing Generalization in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02868","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:b87260e3f6d2e3a5c27ef9fc80152e4197c0ff767fda4eebc5c37a53ec5e668e","target":"record","created_at":"2026-05-17T23:58:35Z","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":"1e68451927de3db4955a9e3d5f529f2971a3e8b683774738d402d57ad0528513","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T01:32:02Z","title_canon_sha256":"ee3d769f0746033feebfb4174de7b0d3bbb86feae03da8434e8d89f3b8307d72"},"schema_version":"1.0","source":{"id":"1812.02868","kind":"arxiv","version":2}},"canonical_sha256":"8ba477687815fee4d171aa6c0d7ebb74a63ea4dc67b92183d046e88a56f49a80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ba477687815fee4d171aa6c0d7ebb74a63ea4dc67b92183d046e88a56f49a80","first_computed_at":"2026-05-17T23:58:35.603665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:35.603665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xWE/d+3z6clmxHnQK4ruruAwO549/e7+xTQ8J3oLdN4ikBzff5TAjS/WEKJjqTXiDVuXz2R2JgaTkPwhEky+Dg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:35.604296Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02868","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b87260e3f6d2e3a5c27ef9fc80152e4197c0ff767fda4eebc5c37a53ec5e668e","sha256:2e7e540f4b192593247659206d72e8f3e252c3bbafdbad0904a2997bb283e448"],"state_sha256":"f1f1f9ac42ba525cbc8d26d13afe7d32ce8e13db93458f4652d9d0bafc7f2c79"}