{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:SMXVIWIHO3MSQI6PMWBT3YYPIU","short_pith_number":"pith:SMXVIWIH","canonical_record":{"source":{"id":"2103.06257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T18:45:48Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"aa5b3f2ea07ae0e77a8345dc7b702d583010d53793cb47c9c9f550727fc26c64","abstract_canon_sha256":"fe0bb454224db28e6d4fb594df92cd007efde427993a4276c7ae55067e47ee0e"},"schema_version":"1.0"},"canonical_sha256":"932f54590776d92823cf65833de30f4510afcf094d0a2458d7fdcfe6796a65a6","source":{"kind":"arxiv","id":"2103.06257","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06257","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06257v2","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06257","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"SMXVIWIHO3MS","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"SMXVIWIHO3MSQI6P","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"SMXVIWIH","created_at":"2026-07-05T04:20:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:SMXVIWIHO3MSQI6PMWBT3YYPIU","target":"record","payload":{"canonical_record":{"source":{"id":"2103.06257","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T18:45:48Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"aa5b3f2ea07ae0e77a8345dc7b702d583010d53793cb47c9c9f550727fc26c64","abstract_canon_sha256":"fe0bb454224db28e6d4fb594df92cd007efde427993a4276c7ae55067e47ee0e"},"schema_version":"1.0"},"canonical_sha256":"932f54590776d92823cf65833de30f4510afcf094d0a2458d7fdcfe6796a65a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:28.053207Z","signature_b64":"z5nXqfqz0Gvd236Mtb7We26ePjm4LPKl4LCnWJtLaLfmUYUhkYH1mYeJ/pM01zHmyXczSk2u43g798y5tKv1BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"932f54590776d92823cf65833de30f4510afcf094d0a2458d7fdcfe6796a65a6","last_reissued_at":"2026-07-05T04:20:28.052747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:28.052747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.06257","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8DsULjXcHlekSowVeud03v00Azz8UW24glKj/sR1oqJej9PACDt3D72Mcdh0p7TK6cq11LhbDPfYH+9+W8fmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:14:58.687014Z"},"content_sha256":"12540570fb8703052214b379253f8782add3902c3279f26f3edf51e9029cfb00","schema_version":"1.0","event_id":"sha256:12540570fb8703052214b379253f8782add3902c3279f26f3edf51e9029cfb00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:SMXVIWIHO3MSQI6PMWBT3YYPIU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Benjamin Eysenbach, Sergey Levine","submitted_at":"2021-03-10T18:45:48Z","abstract_excerpt":"Many potential applications of reinforcement learning (RL) require guarantees that the agent will perform well in the face of disturbances to the dynamics or reward function. In this paper, we prove theoretically that maximum entropy (MaxEnt) RL maximizes a lower bound on a robust RL objective, and thus can be used to learn policies that are robust to some disturbances in the dynamics and the reward function. While this capability of MaxEnt RL has been observed empirically in prior work, to the best of our knowledge our work provides the first rigorous proof and theoretical characterization of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06257","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.06257/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SCB7liBurMZVTEcZEFpfRzRD1eBtZXU2V45EVsDiownvjC/uGUzkUbcsKZDMDSGbEqzGFPI2XWjC7M560kiKBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:14:58.687510Z"},"content_sha256":"f755e385bca7181a1fcb56edb35e3574b04e79bb793acf239d5468b9e26883f0","schema_version":"1.0","event_id":"sha256:f755e385bca7181a1fcb56edb35e3574b04e79bb793acf239d5468b9e26883f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/bundle.json","state_url":"https://pith.science/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T07:14:58Z","links":{"resolver":"https://pith.science/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU","bundle":"https://pith.science/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/bundle.json","state":"https://pith.science/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMXVIWIHO3MSQI6PMWBT3YYPIU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SMXVIWIHO3MSQI6PMWBT3YYPIU","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fe0bb454224db28e6d4fb594df92cd007efde427993a4276c7ae55067e47ee0e","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T18:45:48Z","title_canon_sha256":"aa5b3f2ea07ae0e77a8345dc7b702d583010d53793cb47c9c9f550727fc26c64"},"schema_version":"1.0","source":{"id":"2103.06257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.06257","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2103.06257v2","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.06257","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"SMXVIWIHO3MS","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"SMXVIWIHO3MSQI6P","created_at":"2026-07-05T04:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"SMXVIWIH","created_at":"2026-07-05T04:20:28Z"}],"graph_snapshots":[{"event_id":"sha256:f755e385bca7181a1fcb56edb35e3574b04e79bb793acf239d5468b9e26883f0","target":"graph","created_at":"2026-07-05T04:20:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.06257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many potential applications of reinforcement learning (RL) require guarantees that the agent will perform well in the face of disturbances to the dynamics or reward function. In this paper, we prove theoretically that maximum entropy (MaxEnt) RL maximizes a lower bound on a robust RL objective, and thus can be used to learn policies that are robust to some disturbances in the dynamics and the reward function. While this capability of MaxEnt RL has been observed empirically in prior work, to the best of our knowledge our work provides the first rigorous proof and theoretical characterization of","authors_text":"Benjamin Eysenbach, Sergey Levine","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T18:45:48Z","title":"Maximum Entropy RL (Provably) Solves Some Robust RL Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.06257","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:12540570fb8703052214b379253f8782add3902c3279f26f3edf51e9029cfb00","target":"record","created_at":"2026-07-05T04:20:28Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fe0bb454224db28e6d4fb594df92cd007efde427993a4276c7ae55067e47ee0e","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-10T18:45:48Z","title_canon_sha256":"aa5b3f2ea07ae0e77a8345dc7b702d583010d53793cb47c9c9f550727fc26c64"},"schema_version":"1.0","source":{"id":"2103.06257","kind":"arxiv","version":2}},"canonical_sha256":"932f54590776d92823cf65833de30f4510afcf094d0a2458d7fdcfe6796a65a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"932f54590776d92823cf65833de30f4510afcf094d0a2458d7fdcfe6796a65a6","first_computed_at":"2026-07-05T04:20:28.052747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:28.052747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5nXqfqz0Gvd236Mtb7We26ePjm4LPKl4LCnWJtLaLfmUYUhkYH1mYeJ/pM01zHmyXczSk2u43g798y5tKv1BA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:28.053207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.06257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12540570fb8703052214b379253f8782add3902c3279f26f3edf51e9029cfb00","sha256:f755e385bca7181a1fcb56edb35e3574b04e79bb793acf239d5468b9e26883f0"],"state_sha256":"49e711b2c421ec75b4728af80428e854d23381c0c4d1d29ad82a373f7f21e5a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4CX8omA68Z6it9zEoZB008Q49cXcvfYAjKDXy2AiLmSo3x87LlV5FdZN/ns19n0NpDrfFCUxGQB3ccjC0d0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:14:58.692456Z","bundle_sha256":"cddf4489a96cfc073110a815a1503f90ca5c37c643abded48734b55a9b73a034"}}