{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WIRLTW57SDOFSXKR4BEPSRVCMM","short_pith_number":"pith:WIRLTW57","schema_version":"1.0","canonical_sha256":"b222b9dbbf90dc595d51e048f946a26313897976ac885bc42600731396c98356","source":{"kind":"arxiv","id":"1711.02301","version":5},"attestation_state":"computed","paper":{"title":"Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alex Irpan, Jacob Andreas, Jon Kleinberg, Maithra Raghu, Quoc V. Le, Robert Kleinberg","submitted_at":"2017-11-07T06:16:56Z","abstract_excerpt":"Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization. Here we consider a family of combinatorial games, arising from work of Erdos, Selfridge, and Spencer, and we propose their use as environments for evaluating and comparing different approaches to reinforcement learning. These games have a number of appealing features: they are challenging for current "},"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":"1711.02301","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-07T06:16:56Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"ab55f1046d736150f7753d09c47c3c05c80780da44c079b9e596e18704e39532","abstract_canon_sha256":"f9ff45becf2ba635b6b20c0c7f56108e33977633301505e266a7f61c45c97697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:06.185594Z","signature_b64":"3Jr/aZ6N7YItNmwSfpS1p381LrQ18Ir8twFueAJv0Ml5KtgzJyQ7JcW1FiyFAD9khSJe4C2trn3WmmnM/K4VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b222b9dbbf90dc595d51e048f946a26313897976ac885bc42600731396c98356","last_reissued_at":"2026-05-18T00:12:06.184992Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:06.184992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.AI","authors_text":"Alex Irpan, Jacob Andreas, Jon Kleinberg, Maithra Raghu, Quoc V. Le, Robert Kleinberg","submitted_at":"2017-11-07T06:16:56Z","abstract_excerpt":"Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization. Here we consider a family of combinatorial games, arising from work of Erdos, Selfridge, and Spencer, and we propose their use as environments for evaluating and comparing different approaches to reinforcement learning. These games have a number of appealing features: they are challenging for current "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.02301","kind":"arxiv","version":5},"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":"1711.02301","created_at":"2026-05-18T00:12:06.185081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.02301v5","created_at":"2026-05-18T00:12:06.185081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.02301","created_at":"2026-05-18T00:12:06.185081+00:00"},{"alias_kind":"pith_short_12","alias_value":"WIRLTW57SDOF","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WIRLTW57SDOFSXKR","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WIRLTW57","created_at":"2026-05-18T12:31:53.515858+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/WIRLTW57SDOFSXKR4BEPSRVCMM","json":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM.json","graph_json":"https://pith.science/api/pith-number/WIRLTW57SDOFSXKR4BEPSRVCMM/graph.json","events_json":"https://pith.science/api/pith-number/WIRLTW57SDOFSXKR4BEPSRVCMM/events.json","paper":"https://pith.science/paper/WIRLTW57"},"agent_actions":{"view_html":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM","download_json":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM.json","view_paper":"https://pith.science/paper/WIRLTW57","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/WIRLTW57SDOFSXKR4BEPSRVCMM/graph.json","fetch_events":"https://pith.science/api/pith-number/WIRLTW57SDOFSXKR4BEPSRVCMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM/action/storage_attestation","attest_author":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM/action/author_attestation","sign_citation":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM/action/citation_signature","submit_replication":"https://pith.science/pith/WIRLTW57SDOFSXKR4BEPSRVCMM/action/replication_record"}},"created_at":"2026-05-18T00:12:06.185081+00:00","updated_at":"2026-05-18T00:12:06.185081+00:00"}