{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:62WEWPLBVOOWDW7ESTAOOUV4LY","short_pith_number":"pith:62WEWPLB","schema_version":"1.0","canonical_sha256":"f6ac4b3d61ab9d61dbe494c0e752bc5e2343df5f9ca6a570bf3391da954a8412","source":{"kind":"arxiv","id":"1911.09560","version":1},"attestation_state":"computed","paper":{"title":"Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Agostinelli, Anil Anthony Bharath, Kai Arulkumaran, Marta Sarrico, Pierre Richemond","submitted_at":"2019-11-21T15:54:49Z","abstract_excerpt":"Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn rapidly, retrieving cached values from similar past states. In realistic scenarios, with limited resources and noisy data, maintaining meaningful representations in memory is essential to speed up the learning and avoid catastrophic forgetting. Unfortunately, EC methods have a large space and time complexity. We investigate different solutions to these problem"},"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":"1911.09560","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-21T15:54:49Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"07d65475ad6b8d17b00870dd615da7eca840fd4944b619fb6845ddbd276fdfde","abstract_canon_sha256":"037f40ca886f95694499a6597fa47c033dd52bb7184715f380864707f146c071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:02.212940Z","signature_b64":"1p2uqPObP96wUTC757sXFf+uQdloUCISlrCg4fxElZLaBxoBHi+l8ATB2TQzHk6P9QQTD9BNlF0Pz3zIJ1hDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ac4b3d61ab9d61dbe494c0e752bc5e2343df5f9ca6a570bf3391da954a8412","last_reissued_at":"2026-07-05T00:21:02.212481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:02.212481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea Agostinelli, Anil Anthony Bharath, Kai Arulkumaran, Marta Sarrico, Pierre Richemond","submitted_at":"2019-11-21T15:54:49Z","abstract_excerpt":"Recently, neuro-inspired episodic control (EC) methods have been developed to overcome the data-inefficiency of standard deep reinforcement learning approaches. Using non-/semi-parametric models to estimate the value function, they learn rapidly, retrieving cached values from similar past states. In realistic scenarios, with limited resources and noisy data, maintaining meaningful representations in memory is essential to speed up the learning and avoid catastrophic forgetting. Unfortunately, EC methods have a large space and time complexity. We investigate different solutions to these problem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09560","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.09560/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1911.09560","created_at":"2026-07-05T00:21:02.212548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09560v1","created_at":"2026-07-05T00:21:02.212548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09560","created_at":"2026-07-05T00:21:02.212548+00:00"},{"alias_kind":"pith_short_12","alias_value":"62WEWPLBVOOW","created_at":"2026-07-05T00:21:02.212548+00:00"},{"alias_kind":"pith_short_16","alias_value":"62WEWPLBVOOWDW7E","created_at":"2026-07-05T00:21:02.212548+00:00"},{"alias_kind":"pith_short_8","alias_value":"62WEWPLB","created_at":"2026-07-05T00:21:02.212548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30664","citing_title":"Structure-Induced Information for Rerooting Levin Tree Search","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY","json":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY.json","graph_json":"https://pith.science/api/pith-number/62WEWPLBVOOWDW7ESTAOOUV4LY/graph.json","events_json":"https://pith.science/api/pith-number/62WEWPLBVOOWDW7ESTAOOUV4LY/events.json","paper":"https://pith.science/paper/62WEWPLB"},"agent_actions":{"view_html":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY","download_json":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY.json","view_paper":"https://pith.science/paper/62WEWPLB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09560&json=true","fetch_graph":"https://pith.science/api/pith-number/62WEWPLBVOOWDW7ESTAOOUV4LY/graph.json","fetch_events":"https://pith.science/api/pith-number/62WEWPLBVOOWDW7ESTAOOUV4LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY/action/storage_attestation","attest_author":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY/action/author_attestation","sign_citation":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY/action/citation_signature","submit_replication":"https://pith.science/pith/62WEWPLBVOOWDW7ESTAOOUV4LY/action/replication_record"}},"created_at":"2026-07-05T00:21:02.212548+00:00","updated_at":"2026-07-05T00:21:02.212548+00:00"}