{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ROSHO2DYCX7OJULRVJWA27V3OS","short_pith_number":"pith:ROSHO2DY","schema_version":"1.0","canonical_sha256":"8ba477687815fee4d171aa6c0d7ebb74a63ea4dc67b92183d046e88a56f49a80","source":{"kind":"arxiv","id":"1812.02868","version":2},"attestation_state":"computed","paper":{"title":"Measuring and Characterizing Generalization in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akanksha Atrey, David Jensen, Emma Tosch, Jun Ki Lee, Michael Littman, Sam Witty","submitted_at":"2018-12-07T01:32:02Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1812.02868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-07T01:32:02Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"ee3d769f0746033feebfb4174de7b0d3bbb86feae03da8434e8d89f3b8307d72","abstract_canon_sha256":"1e68451927de3db4955a9e3d5f529f2971a3e8b683774738d402d57ad0528513"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:35.604296Z","signature_b64":"xWE/d+3z6clmxHnQK4ruruAwO549/e7+xTQ8J3oLdN4ikBzff5TAjS/WEKJjqTXiDVuXz2R2JgaTkPwhEky+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba477687815fee4d171aa6c0d7ebb74a63ea4dc67b92183d046e88a56f49a80","last_reissued_at":"2026-05-17T23:58:35.603665Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:35.603665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring and Characterizing Generalization in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akanksha Atrey, David Jensen, Emma Tosch, Jun Ki Lee, Michael Littman, Sam Witty","submitted_at":"2018-12-07T01:32:02Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02868","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1812.02868","created_at":"2026-05-17T23:58:35.603768+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02868v2","created_at":"2026-05-17T23:58:35.603768+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02868","created_at":"2026-05-17T23:58:35.603768+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROSHO2DYCX7O","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROSHO2DYCX7OJULR","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROSHO2DY","created_at":"2026-05-18T12:32:50.500415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS","json":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS.json","graph_json":"https://pith.science/api/pith-number/ROSHO2DYCX7OJULRVJWA27V3OS/graph.json","events_json":"https://pith.science/api/pith-number/ROSHO2DYCX7OJULRVJWA27V3OS/events.json","paper":"https://pith.science/paper/ROSHO2DY"},"agent_actions":{"view_html":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS","download_json":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS.json","view_paper":"https://pith.science/paper/ROSHO2DY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02868&json=true","fetch_graph":"https://pith.science/api/pith-number/ROSHO2DYCX7OJULRVJWA27V3OS/graph.json","fetch_events":"https://pith.science/api/pith-number/ROSHO2DYCX7OJULRVJWA27V3OS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS/action/storage_attestation","attest_author":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS/action/author_attestation","sign_citation":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS/action/citation_signature","submit_replication":"https://pith.science/pith/ROSHO2DYCX7OJULRVJWA27V3OS/action/replication_record"}},"created_at":"2026-05-17T23:58:35.603768+00:00","updated_at":"2026-05-17T23:58:35.603768+00:00"}