{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:HC2OFER5UZISRTR7LRPV7BCNNZ","short_pith_number":"pith:HC2OFER5","schema_version":"1.0","canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","source":{"kind":"arxiv","id":"1610.01283","version":4},"attestation_state":"computed","paper":{"title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Balaraman Ravindran, Sarvjeet Ghotra, Sergey Levine","submitted_at":"2016-10-05T06:51:58Z","abstract_excerpt":"Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based methods where the real-world target domain is approximated using a simulated source domain provide an avenue to tackle the above challenges by augmenting real data with simulated data. However, discrepancies between the simulated source domain and the target domain pose a challenge for simulated training. We introduce the EPOpt algorithm, which uses an ense"},"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":"1610.01283","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ef6754fbd12236831f5fd993989d02e4ecd0cc5f2a7bd9df742d9e41545b8946","abstract_canon_sha256":"698a9923894aed98a468670270840cd4355488f0a0a12ecf16207f98a3785e21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:32.017263Z","signature_b64":"BvMXcDFSOBj18j2or6Ut/WpukuphqgEBD8f6HkJ2YT0rxfv3P4jzWDX1maUStptHmUIRWUyDvu7exTA0531mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","last_reissued_at":"2026-05-18T00:49:32.016714Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:32.016714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Balaraman Ravindran, Sarvjeet Ghotra, Sergey Levine","submitted_at":"2016-10-05T06:51:58Z","abstract_excerpt":"Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based methods where the real-world target domain is approximated using a simulated source domain provide an avenue to tackle the above challenges by augmenting real data with simulated data. However, discrepancies between the simulated source domain and the target domain pose a challenge for simulated training. We introduce the EPOpt algorithm, which uses an ense"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01283","kind":"arxiv","version":4},"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":"1610.01283","created_at":"2026-05-18T00:49:32.016801+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.01283v4","created_at":"2026-05-18T00:49:32.016801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01283","created_at":"2026-05-18T00:49:32.016801+00:00"},{"alias_kind":"pith_short_12","alias_value":"HC2OFER5UZIS","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"HC2OFER5UZISRTR7","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"HC2OFER5","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09183","citing_title":"Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06500","citing_title":"Operator-Guided Invariance Learning for Continuous Reinforcement Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10974","citing_title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ","json":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ.json","graph_json":"https://pith.science/api/pith-number/HC2OFER5UZISRTR7LRPV7BCNNZ/graph.json","events_json":"https://pith.science/api/pith-number/HC2OFER5UZISRTR7LRPV7BCNNZ/events.json","paper":"https://pith.science/paper/HC2OFER5"},"agent_actions":{"view_html":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ","download_json":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ.json","view_paper":"https://pith.science/paper/HC2OFER5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.01283&json=true","fetch_graph":"https://pith.science/api/pith-number/HC2OFER5UZISRTR7LRPV7BCNNZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HC2OFER5UZISRTR7LRPV7BCNNZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/action/storage_attestation","attest_author":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/action/author_attestation","sign_citation":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/action/citation_signature","submit_replication":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/action/replication_record"}},"created_at":"2026-05-18T00:49:32.016801+00:00","updated_at":"2026-05-18T00:49:32.016801+00:00"}