{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DPK5LA6IPXEAYJW7IJV4MDAYI4","short_pith_number":"pith:DPK5LA6I","canonical_record":{"source":{"id":"1905.07628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-18T19:20:04Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"710f98091cb2c45dc0a08c8748ffb96bf844016187a177cc79637614fa9a1f66","abstract_canon_sha256":"640942edf55712616ce0b1b636739b532637bcaef891e196f4d72daf51811ad8"},"schema_version":"1.0"},"canonical_sha256":"1bd5d583c87dc80c26df426bc60c184701deb0cabe410f38cc284ce4c5329d77","source":{"kind":"arxiv","id":"1905.07628","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07628","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07628v1","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07628","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"DPK5LA6IPXEA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DPK5LA6IPXEAYJW7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DPK5LA6I","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DPK5LA6IPXEAYJW7IJV4MDAYI4","target":"record","payload":{"canonical_record":{"source":{"id":"1905.07628","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-18T19:20:04Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"710f98091cb2c45dc0a08c8748ffb96bf844016187a177cc79637614fa9a1f66","abstract_canon_sha256":"640942edf55712616ce0b1b636739b532637bcaef891e196f4d72daf51811ad8"},"schema_version":"1.0"},"canonical_sha256":"1bd5d583c87dc80c26df426bc60c184701deb0cabe410f38cc284ce4c5329d77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:49.030890Z","signature_b64":"o/C0wGfNLfpPrndIBb/4/wvrSJJQaVQLc+X0T4tenW8p+yntrCOWu0XQ5Ey//Ly6jpFFMebAxp472oqMiVJgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bd5d583c87dc80c26df426bc60c184701deb0cabe410f38cc284ce4c5329d77","last_reissued_at":"2026-05-17T23:45:49.030183Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:49.030183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.07628","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qZuxMU7DYUT9gRHFxXM4PSUmcs1FeadZLocs+OBo//2cV593wuwWpK3HEX+B6EU/jypsqUVidvyRKXefaOQ/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:50:01.515505Z"},"content_sha256":"c0bb453bd5ffcd2f5dcea5440b7d567dca5b3a52acfe97f7d7abd976fe003d34","schema_version":"1.0","event_id":"sha256:c0bb453bd5ffcd2f5dcea5440b7d567dca5b3a52acfe97f7d7abd976fe003d34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DPK5LA6IPXEAYJW7IJV4MDAYI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evolving Rewards to Automate Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aleksandra Faust, Anthony Francis, Dar Mehta","submitted_at":"2019-05-18T19:20:04Z","abstract_excerpt":"Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex rewards, which require tedious hand-tuning. We automate the reward search with AutoRL, an evolutionary layer over standard RL that treats reward tuning as hyperparameter optimization and trains a population of RL agents to find a reward that maximizes the task objective. AutoRL, evaluated on four Mujoco continuous control tasks over two RL algorithms, shows improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07628","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xl9Ev5UScZrOF84sNVHcMKkwkERkNx2Kzmb2QSkd0hUncK0HzU7w9WBR2OkgbBS3oon6aWt/A5FgWVvlJoOJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:50:01.515925Z"},"content_sha256":"b31ace44881e6d2f7bfd135e9e83db1a5926108e4586f97a74a252066ed05518","schema_version":"1.0","event_id":"sha256:b31ace44881e6d2f7bfd135e9e83db1a5926108e4586f97a74a252066ed05518"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/bundle.json","state_url":"https://pith.science/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/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":"2026-05-28T21:50:01Z","links":{"resolver":"https://pith.science/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4","bundle":"https://pith.science/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/bundle.json","state":"https://pith.science/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPK5LA6IPXEAYJW7IJV4MDAYI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DPK5LA6IPXEAYJW7IJV4MDAYI4","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":"640942edf55712616ce0b1b636739b532637bcaef891e196f4d72daf51811ad8","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-18T19:20:04Z","title_canon_sha256":"710f98091cb2c45dc0a08c8748ffb96bf844016187a177cc79637614fa9a1f66"},"schema_version":"1.0","source":{"id":"1905.07628","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.07628","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"1905.07628v1","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07628","created_at":"2026-05-17T23:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"DPK5LA6IPXEA","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DPK5LA6IPXEAYJW7","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DPK5LA6I","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:b31ace44881e6d2f7bfd135e9e83db1a5926108e4586f97a74a252066ed05518","target":"graph","created_at":"2026-05-17T23:45:49Z","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"},"paper":{"abstract_excerpt":"Many continuous control tasks have easily formulated objectives, yet using them directly as a reward in reinforcement learning (RL) leads to suboptimal policies. Therefore, many classical control tasks guide RL training using complex rewards, which require tedious hand-tuning. We automate the reward search with AutoRL, an evolutionary layer over standard RL that treats reward tuning as hyperparameter optimization and trains a population of RL agents to find a reward that maximizes the task objective. AutoRL, evaluated on four Mujoco continuous control tasks over two RL algorithms, shows improv","authors_text":"Aleksandra Faust, Anthony Francis, Dar Mehta","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-18T19:20:04Z","title":"Evolving Rewards to Automate Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07628","kind":"arxiv","version":1},"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:c0bb453bd5ffcd2f5dcea5440b7d567dca5b3a52acfe97f7d7abd976fe003d34","target":"record","created_at":"2026-05-17T23:45:49Z","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":"640942edf55712616ce0b1b636739b532637bcaef891e196f4d72daf51811ad8","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-18T19:20:04Z","title_canon_sha256":"710f98091cb2c45dc0a08c8748ffb96bf844016187a177cc79637614fa9a1f66"},"schema_version":"1.0","source":{"id":"1905.07628","kind":"arxiv","version":1}},"canonical_sha256":"1bd5d583c87dc80c26df426bc60c184701deb0cabe410f38cc284ce4c5329d77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bd5d583c87dc80c26df426bc60c184701deb0cabe410f38cc284ce4c5329d77","first_computed_at":"2026-05-17T23:45:49.030183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:49.030183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o/C0wGfNLfpPrndIBb/4/wvrSJJQaVQLc+X0T4tenW8p+yntrCOWu0XQ5Ey//Ly6jpFFMebAxp472oqMiVJgDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:49.030890Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.07628","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0bb453bd5ffcd2f5dcea5440b7d567dca5b3a52acfe97f7d7abd976fe003d34","sha256:b31ace44881e6d2f7bfd135e9e83db1a5926108e4586f97a74a252066ed05518"],"state_sha256":"2fa2e89efdc1a63e233ec2f64d4f70053d87ec3b2a18762df549067b4cd7bb98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"56IQQ3OgA6oLaSdU6zqYNHMJfS+tt2s6JtR1wd7N+J58AGdVHg/HalVtyVda4XObKpnC4n60dVRfOVknX8O/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:50:01.519245Z","bundle_sha256":"92f679ba83f36da5a8866b7114439160fa361338ff06b08934d14f8cba9001ab"}}