{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QKIHKSQ5FKTWK7IXZWQ64MCAGQ","short_pith_number":"pith:QKIHKSQ5","schema_version":"1.0","canonical_sha256":"8290754a1d2aa7657d17cda1ee304034087ad2106ba3ba499b7c7bc8eabaf8e1","source":{"kind":"arxiv","id":"1810.12282","version":2},"attestation_state":"computed","paper":{"title":"Assessing 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":"Charles Packer, Dawn Song, Jernej Kos, Katelyn Gao, Philipp Kr\\\"ahenb\\\"uhl, Vladlen Koltun","submitted_at":"2018-10-29T17:51:46Z","abstract_excerpt":"Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation. The literature lacks a controlled assessment of the merits of different generalization schemes. Our aim is to catalyze community-wide progress on generalization in deep RL. To this end, we present a benchmark and experimental protocol, and condu"},"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":"1810.12282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T17:51:46Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5bf21288e73dafd65f57d4d2b4f55ca44e7d854ad5b0217c28150b23bd2bd222","abstract_canon_sha256":"ad8549035213f2c152cefe179fcf51b8f08bed5af4ced10909d2fb1245d5fbc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:14.081513Z","signature_b64":"74Xx/wi6jK5VwpLaYrt+8ig3HxLDovZ0pMK69MOJ1U0u0e/GB/hbvtx3qJa2khhpSFc1j+nWLYcwnAugD+p3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8290754a1d2aa7657d17cda1ee304034087ad2106ba3ba499b7c7bc8eabaf8e1","last_reissued_at":"2026-05-17T23:51:14.080385Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:14.080385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing 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":"Charles Packer, Dawn Song, Jernej Kos, Katelyn Gao, Philipp Kr\\\"ahenb\\\"uhl, Vladlen Koltun","submitted_at":"2018-10-29T17:51:46Z","abstract_excerpt":"Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation. The literature lacks a controlled assessment of the merits of different generalization schemes. Our aim is to catalyze community-wide progress on generalization in deep RL. To this end, we present a benchmark and experimental protocol, and condu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12282","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":"1810.12282","created_at":"2026-05-17T23:51:14.081052+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12282v2","created_at":"2026-05-17T23:51:14.081052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12282","created_at":"2026-05-17T23:51:14.081052+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKIHKSQ5FKTW","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKIHKSQ5FKTWK7IX","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKIHKSQ5","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1907.02050","citing_title":"Reasoning and Generalization in RL: A Tool Use Perspective","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2507.04356","citing_title":"Mission-Aligned Learning-Informed Control of Autonomous Systems: Formulation and Foundations","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14535","citing_title":"Visualizing Critic Match Loss Landscapes for Interpretation of Online Reinforcement Learning Control Algorithms","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06992","citing_title":"Why Does Agentic Safety Fail to Generalize Across Tasks?","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02867","citing_title":"Enhancing RL Generalizability in Robotics through SHAP Analysis of Algorithms and Hyperparameters","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ","json":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ.json","graph_json":"https://pith.science/api/pith-number/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/graph.json","events_json":"https://pith.science/api/pith-number/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/events.json","paper":"https://pith.science/paper/QKIHKSQ5"},"agent_actions":{"view_html":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ","download_json":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ.json","view_paper":"https://pith.science/paper/QKIHKSQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12282&json=true","fetch_graph":"https://pith.science/api/pith-number/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/action/storage_attestation","attest_author":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/action/author_attestation","sign_citation":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/action/citation_signature","submit_replication":"https://pith.science/pith/QKIHKSQ5FKTWK7IXZWQ64MCAGQ/action/replication_record"}},"created_at":"2026-05-17T23:51:14.081052+00:00","updated_at":"2026-05-17T23:51:14.081052+00:00"}