{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WASUUF7BQAT53G7JCADYMVLETM","short_pith_number":"pith:WASUUF7B","schema_version":"1.0","canonical_sha256":"b0254a17e18027dd9be910078655649b076d51500dfe9d50874e6391de7a2b8b","source":{"kind":"arxiv","id":"1903.02710","version":1},"attestation_state":"computed","paper":{"title":"Concurrent Meta Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov, Sai Bhargav Yalamanchi, Soham Ghosh, Varsha Chinnaobireddy, Yuhuai Wu","submitted_at":"2019-03-07T03:28:41Z","abstract_excerpt":"State-of-the-art meta reinforcement learning algorithms typically assume the setting of a single agent interacting with its environment in a sequential manner. A negative side-effect of this sequential execution paradigm is that, as the environment becomes more and more challenging, and thus requiring more interaction episodes for the meta-learner, it needs the agent to reason over longer and longer time-scales. To combat the difficulty of long time-scale credit assignment, we propose an alternative parallel framework, which we name \"Concurrent Meta-Reinforcement Learning\" (CMRL), that transfo"},"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":"1903.02710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-03-07T03:28:41Z","cross_cats_sorted":[],"title_canon_sha256":"947adf6e9951f5427f4e8b8a8373129413df5b4af2b11787b9cfd287ff744d7d","abstract_canon_sha256":"01004c73413b37ebdb0119ae26b4271ee504154c6824888b9dca4f39a5056166"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:51.380376Z","signature_b64":"1AOn32biT0iTVgITEELXtFfTjI5QrXaMUv0fzMJx7M0wxLfKD6R6/h9rfwGc6+Gb3fdLgp8NTjJkXaOqlrmfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0254a17e18027dd9be910078655649b076d51500dfe9d50874e6391de7a2b8b","last_reissued_at":"2026-05-17T23:51:51.379651Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:51.379651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concurrent Meta Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Emilio Parisotto, Ruslan Salakhutdinov, Sai Bhargav Yalamanchi, Soham Ghosh, Varsha Chinnaobireddy, Yuhuai Wu","submitted_at":"2019-03-07T03:28:41Z","abstract_excerpt":"State-of-the-art meta reinforcement learning algorithms typically assume the setting of a single agent interacting with its environment in a sequential manner. A negative side-effect of this sequential execution paradigm is that, as the environment becomes more and more challenging, and thus requiring more interaction episodes for the meta-learner, it needs the agent to reason over longer and longer time-scales. To combat the difficulty of long time-scale credit assignment, we propose an alternative parallel framework, which we name \"Concurrent Meta-Reinforcement Learning\" (CMRL), that transfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02710","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":"1903.02710","created_at":"2026-05-17T23:51:51.379739+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.02710v1","created_at":"2026-05-17T23:51:51.379739+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02710","created_at":"2026-05-17T23:51:51.379739+00:00"},{"alias_kind":"pith_short_12","alias_value":"WASUUF7BQAT5","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WASUUF7BQAT53G7J","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WASUUF7B","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":118,"is_internal_anchor":true},{"citing_arxiv_id":"1910.07113","citing_title":"Solving Rubik's Cube with a Robot Hand","ref_index":79,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM","json":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM.json","graph_json":"https://pith.science/api/pith-number/WASUUF7BQAT53G7JCADYMVLETM/graph.json","events_json":"https://pith.science/api/pith-number/WASUUF7BQAT53G7JCADYMVLETM/events.json","paper":"https://pith.science/paper/WASUUF7B"},"agent_actions":{"view_html":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM","download_json":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM.json","view_paper":"https://pith.science/paper/WASUUF7B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.02710&json=true","fetch_graph":"https://pith.science/api/pith-number/WASUUF7BQAT53G7JCADYMVLETM/graph.json","fetch_events":"https://pith.science/api/pith-number/WASUUF7BQAT53G7JCADYMVLETM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM/action/storage_attestation","attest_author":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM/action/author_attestation","sign_citation":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM/action/citation_signature","submit_replication":"https://pith.science/pith/WASUUF7BQAT53G7JCADYMVLETM/action/replication_record"}},"created_at":"2026-05-17T23:51:51.379739+00:00","updated_at":"2026-05-17T23:51:51.379739+00:00"}