{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:ZGEYL3EKFFA4LMRNPJ3HCQNAJI","short_pith_number":"pith:ZGEYL3EK","schema_version":"1.0","canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","source":{"kind":"arxiv","id":"1301.0567","version":1},"attestation_state":"computed","paper":{"title":"The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leslie Pack Kaelbling, Natalia Gardiol, Sarah Finney, Tim Oates","submitted_at":"2012-12-12T15:56:10Z","abstract_excerpt":"Most reinforcement learning methods operate on propositional representations of the world state.  Such representations are often intractably large and generalize poorly.  Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods.  Yet, there are few experiments on learning with deictic representations reported in the literature.  In this paper we explore the effectiveness of two forms of deictic representation and a na\\\"{i}ve propositional representation in a simple blocks-world domain.  "},"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":"1301.0567","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-12-12T15:56:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"85a62bd2bcad0e070f3721bbbed8d122f261ed01a95428a83f0129160a4c4a31","abstract_canon_sha256":"3fabf71c89ff21d66159baf932c94517b31a08e4ff1edd482ed2e26a3ec3821e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:37:18.492659Z","signature_b64":"WrsP56tEFEM7t7F7nvBQycxM5omDM8Vsn/auPYIpX2ubw8y4II195w8LSTGh4PU7BAXuEPuFlLYANR/AMb2aBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c98985ec8a2941c5b22d7a767141a04a080eb0c3025b64932deeefe60bfc24e2","last_reissued_at":"2026-05-18T03:37:18.492001Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:37:18.492001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Thing That We Tried Didn't Work Very Well : Deictic Representation in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leslie Pack Kaelbling, Natalia Gardiol, Sarah Finney, Tim Oates","submitted_at":"2012-12-12T15:56:10Z","abstract_excerpt":"Most reinforcement learning methods operate on propositional representations of the world state.  Such representations are often intractably large and generalize poorly.  Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods.  Yet, there are few experiments on learning with deictic representations reported in the literature.  In this paper we explore the effectiveness of two forms of deictic representation and a na\\\"{i}ve propositional representation in a simple blocks-world domain.  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.0567","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":"1301.0567","created_at":"2026-05-18T03:37:18.492103+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.0567v1","created_at":"2026-05-18T03:37:18.492103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.0567","created_at":"2026-05-18T03:37:18.492103+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZGEYL3EKFFA4","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZGEYL3EKFFA4LMRN","created_at":"2026-05-18T12:27:30.460161+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZGEYL3EK","created_at":"2026-05-18T12:27:30.460161+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/ZGEYL3EKFFA4LMRNPJ3HCQNAJI","json":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI.json","graph_json":"https://pith.science/api/pith-number/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/graph.json","events_json":"https://pith.science/api/pith-number/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/events.json","paper":"https://pith.science/paper/ZGEYL3EK"},"agent_actions":{"view_html":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI","download_json":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI.json","view_paper":"https://pith.science/paper/ZGEYL3EK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.0567&json=true","fetch_graph":"https://pith.science/api/pith-number/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/graph.json","fetch_events":"https://pith.science/api/pith-number/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/action/storage_attestation","attest_author":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/action/author_attestation","sign_citation":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/action/citation_signature","submit_replication":"https://pith.science/pith/ZGEYL3EKFFA4LMRNPJ3HCQNAJI/action/replication_record"}},"created_at":"2026-05-18T03:37:18.492103+00:00","updated_at":"2026-05-18T03:37:18.492103+00:00"}