{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WL2ENWWRC4M6UUZMHRZCN4VF5L","short_pith_number":"pith:WL2ENWWR","schema_version":"1.0","canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","source":{"kind":"arxiv","id":"1611.05763","version":3},"attestation_state":"computed","paper":{"title":"Learning to reinforcement learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Blundell, Dharshan Kumaran, Dhruva Tirumala, Hubert Soyer, Jane X Wang, Joel Z Leibo, Matt Botvinick, Remi Munos, Zeb Kurth-Nelson","submitted_at":"2016-11-17T16:29:11Z","abstract_excerpt":"In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rapidly to new tasks. In the present work we introduce a novel approach to this challenge, which we refer to as deep meta-reinforcement learning. Previous work has shown that recurrent networks can support meta-learning in a fully supervised context. We extend this approach to the R"},"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":"1611.05763","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-17T16:29:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8ee3556dfddc72ddf7cf235e11b7c6579d128d771cf60f0c807b207004c13b14","abstract_canon_sha256":"b62dae1211324e21f9250ae4deeea9f588474cdbf809fd3e76391371ecad238e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:22.467790Z","signature_b64":"iI2zxom9Z4f2oEqhxhKV2jl9m2kQX2dxU0rnJzEsjLEuLi4rsFeJa/9/8GJLn1vJpeOb5AnclXgiEyKcd+inBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2f446dad11719ea532c3c7226f2a5eac69bd0f1e3279a4a490104d2db8965b2","last_reissued_at":"2026-05-18T00:52:22.467230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:22.467230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to reinforcement learn","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Charles Blundell, Dharshan Kumaran, Dhruva Tirumala, Hubert Soyer, Jane X Wang, Joel Z Leibo, Matt Botvinick, Remi Munos, Zeb Kurth-Nelson","submitted_at":"2016-11-17T16:29:11Z","abstract_excerpt":"In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rapidly to new tasks. In the present work we introduce a novel approach to this challenge, which we refer to as deep meta-reinforcement learning. Previous work has shown that recurrent networks can support meta-learning in a fully supervised context. We extend this approach to the R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.05763","kind":"arxiv","version":3},"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":"1611.05763","created_at":"2026-05-18T00:52:22.467337+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.05763v3","created_at":"2026-05-18T00:52:22.467337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.05763","created_at":"2026-05-18T00:52:22.467337+00:00"},{"alias_kind":"pith_short_12","alias_value":"WL2ENWWRC4M6","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WL2ENWWRC4M6UUZM","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WL2ENWWR","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"1907.01475","citing_title":"Generalizing from a few environments in safety-critical reinforcement learning","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06077","citing_title":"Evolvability ES: Scalable and Direct Optimization of Evolvability","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11740","citing_title":"Environment Probing Interaction Policies","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2505.17323","citing_title":"Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18841","citing_title":"From Cumulative Constraints to Adaptive Runtime Safety Control for Nonstationary Reinforcement Learning","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18842","citing_title":"Safe Continual Reinforcement Learning under Nonstationarity via Adaptive Safety Constraints","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18704","citing_title":"Learned Memory Attenuation in Sage-Husa Kalman Filters for Robust UAV State Estimation","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2509.11481","citing_title":"RAPTOR: A Foundation Policy for Quadrotor Control","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2512.20974","citing_title":"Generalised Linear Models in Deep Bayesian RL with Learnable Basis Functions","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"1906.01820","citing_title":"Risks from Learned Optimization in Advanced Machine Learning Systems","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2408.08435","citing_title":"Automated Design of Agentic Systems","ref_index":217,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13821","citing_title":"Harnessing Agentic Evolution","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"1806.01261","citing_title":"Relational inductive biases, deep learning, and graph networks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08450","citing_title":"Zero-shot Imitation Learning by Latent Topology Mapping","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"1710.05941","citing_title":"Searching for Activation Functions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09009","citing_title":"Large Language Models for Sequential Decision-Making: Improving In-Context Learning via Supervised Fine-Tuning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11914","citing_title":"Self-Monitoring Benefits from Structural Integration: Lessons from Metacognition in Continuous-Time Multi-Timescale Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19064","citing_title":"The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L","json":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L.json","graph_json":"https://pith.science/api/pith-number/WL2ENWWRC4M6UUZMHRZCN4VF5L/graph.json","events_json":"https://pith.science/api/pith-number/WL2ENWWRC4M6UUZMHRZCN4VF5L/events.json","paper":"https://pith.science/paper/WL2ENWWR"},"agent_actions":{"view_html":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L","download_json":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L.json","view_paper":"https://pith.science/paper/WL2ENWWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.05763&json=true","fetch_graph":"https://pith.science/api/pith-number/WL2ENWWRC4M6UUZMHRZCN4VF5L/graph.json","fetch_events":"https://pith.science/api/pith-number/WL2ENWWRC4M6UUZMHRZCN4VF5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/action/storage_attestation","attest_author":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/action/author_attestation","sign_citation":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/action/citation_signature","submit_replication":"https://pith.science/pith/WL2ENWWRC4M6UUZMHRZCN4VF5L/action/replication_record"}},"created_at":"2026-05-18T00:52:22.467337+00:00","updated_at":"2026-05-18T00:52:22.467337+00:00"}