{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AZKTROVPJOYQDHZMYHTEU5BFQI","short_pith_number":"pith:AZKTROVP","schema_version":"1.0","canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","source":{"kind":"arxiv","id":"1903.06309","version":2},"attestation_state":"computed","paper":{"title":"Adaptive Variance for Changing Sparse-Reward Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carlos Florensa, David Held, Pengsheng Guo, Xingyu Lin","submitted_at":"2019-03-15T00:40:59Z","abstract_excerpt":"Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of s"},"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":"1903.06309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-03-15T00:40:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"624210dad6d0949939a0ff4e47048bf0bfa54434abc5785e2b1090ac5e547499","abstract_canon_sha256":"5e7b23880d584b251be4701080df11d9c1c96ed44511dcc756645a4fbd7bc27d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:40.934418Z","signature_b64":"sQNSDTflmZ3qX6pigtwHhs+pNdI0KICqAPrABew6WENvUk7MGE/IBASTDV3KUIJVBrDGbyPEqZJ6gzE545CQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065538baaf4bb1019f2cc1e64a742582218b16f490438ba9385fb1462af64ca2","last_reissued_at":"2026-05-17T23:46:40.933708Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:40.933708Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Variance for Changing Sparse-Reward Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Carlos Florensa, David Held, Pengsheng Guo, Xingyu Lin","submitted_at":"2019-03-15T00:40:59Z","abstract_excerpt":"Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.06309","kind":"arxiv","version":2},"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":"1903.06309","created_at":"2026-05-17T23:46:40.933814+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.06309v2","created_at":"2026-05-17T23:46:40.933814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.06309","created_at":"2026-05-17T23:46:40.933814+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZKTROVPJOYQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZKTROVPJOYQDHZM","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZKTROVP","created_at":"2026-05-18T12:33:12.712433+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/AZKTROVPJOYQDHZMYHTEU5BFQI","json":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI.json","graph_json":"https://pith.science/api/pith-number/AZKTROVPJOYQDHZMYHTEU5BFQI/graph.json","events_json":"https://pith.science/api/pith-number/AZKTROVPJOYQDHZMYHTEU5BFQI/events.json","paper":"https://pith.science/paper/AZKTROVP"},"agent_actions":{"view_html":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI","download_json":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI.json","view_paper":"https://pith.science/paper/AZKTROVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.06309&json=true","fetch_graph":"https://pith.science/api/pith-number/AZKTROVPJOYQDHZMYHTEU5BFQI/graph.json","fetch_events":"https://pith.science/api/pith-number/AZKTROVPJOYQDHZMYHTEU5BFQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/action/storage_attestation","attest_author":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/action/author_attestation","sign_citation":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/action/citation_signature","submit_replication":"https://pith.science/pith/AZKTROVPJOYQDHZMYHTEU5BFQI/action/replication_record"}},"created_at":"2026-05-17T23:46:40.933814+00:00","updated_at":"2026-05-17T23:46:40.933814+00:00"}