{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ZPFLSRA2247YNJSS4YDTUWSXME","short_pith_number":"pith:ZPFLSRA2","schema_version":"1.0","canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","source":{"kind":"arxiv","id":"1606.02396","version":1},"attestation_state":"computed","paper":{"title":"Deep Successor Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Ardavan Saeedi, Samuel J. Gershman, Simanta Gautam, Tejas D. Kulkarni","submitted_at":"2016-06-08T04:48:49Z","abstract_excerpt":"Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we "},"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":"1606.02396","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-08T04:48:49Z","cross_cats_sorted":["cs.AI","cs.LG","cs.NE"],"title_canon_sha256":"269b0fb478a391bcf7345c4e9359e42c3d4ff8f11e5af0cf74a499e2e7757ea3","abstract_canon_sha256":"3bd9f1b0faf0fef375ee534ee22a0b41c7dbc13d9f594ec0db3d41fb3abe434a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:41.451900Z","signature_b64":"JF+YdcykHY4VNbClk5pcCA54lUjkUBFQVMSnYnubNQjzxA0yj4AkkBUCogfPhn7rZPXMQhXgCVdfjLhXpNEnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbcab9441ad73f86a652e6073a5a57610382de5bfdcb098b909e4a291f2013ed","last_reissued_at":"2026-05-18T01:12:41.451550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:41.451550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Successor Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Ardavan Saeedi, Samuel J. Gershman, Simanta Gautam, Tejas D. Kulkarni","submitted_at":"2016-06-08T04:48:49Z","abstract_excerpt":"Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can be computed as the inner product between the successor map and the reward weights. In this paper, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02396","kind":"arxiv","version":1},"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":"1606.02396","created_at":"2026-05-18T01:12:41.451606+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.02396v1","created_at":"2026-05-18T01:12:41.451606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02396","created_at":"2026-05-18T01:12:41.451606+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPFLSRA2247Y","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPFLSRA2247YNJSS","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPFLSRA2","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"1906.09237","citing_title":"Shaping Belief States with Generative Environment Models for RL","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"1906.09480","citing_title":"A neurally plausible model learns successor representations in partially observable environments","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2603.20103","citing_title":"Spectral Alignment in Forward-Backward Representations via Temporal Abstraction","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24532","citing_title":"A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME","json":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME.json","graph_json":"https://pith.science/api/pith-number/ZPFLSRA2247YNJSS4YDTUWSXME/graph.json","events_json":"https://pith.science/api/pith-number/ZPFLSRA2247YNJSS4YDTUWSXME/events.json","paper":"https://pith.science/paper/ZPFLSRA2"},"agent_actions":{"view_html":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME","download_json":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME.json","view_paper":"https://pith.science/paper/ZPFLSRA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.02396&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPFLSRA2247YNJSS4YDTUWSXME/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPFLSRA2247YNJSS4YDTUWSXME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/action/storage_attestation","attest_author":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/action/author_attestation","sign_citation":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/action/citation_signature","submit_replication":"https://pith.science/pith/ZPFLSRA2247YNJSS4YDTUWSXME/action/replication_record"}},"created_at":"2026-05-18T01:12:41.451606+00:00","updated_at":"2026-05-18T01:12:41.451606+00:00"}