{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OY6UIUB3I5I3RU2N7ZVQQZOTTO","short_pith_number":"pith:OY6UIUB3","canonical_record":{"source":{"id":"1805.11074","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:31:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6ad4503a61e54aa72d763a4654ce6df6dbdae9b9f11d9fdc8100fb581baa447a","abstract_canon_sha256":"e8c4da5368282395e3a8694b960f3bfa5251ba844a65fe5e68c2005f31c6d322"},"schema_version":"1.0"},"canonical_sha256":"763d44503b4751b8d34dfe6b0865d39b8c68e6f41ca8e73089ab997924d53d9d","source":{"kind":"arxiv","id":"1805.11074","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11074","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11074v3","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11074","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"OY6UIUB3I5I3","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OY6UIUB3I5I3RU2N","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OY6UIUB3","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OY6UIUB3I5I3RU2N7ZVQQZOTTO","target":"record","payload":{"canonical_record":{"source":{"id":"1805.11074","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:31:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6ad4503a61e54aa72d763a4654ce6df6dbdae9b9f11d9fdc8100fb581baa447a","abstract_canon_sha256":"e8c4da5368282395e3a8694b960f3bfa5251ba844a65fe5e68c2005f31c6d322"},"schema_version":"1.0"},"canonical_sha256":"763d44503b4751b8d34dfe6b0865d39b8c68e6f41ca8e73089ab997924d53d9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:31.896191Z","signature_b64":"DnV0aGSk8yWGXUvEfa80jXX9kd6mHtRegM4R0N6wi3IBy410y2DtT6LlWwuxxGjqZ1m+Wc2pco8QkE33GXy1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"763d44503b4751b8d34dfe6b0865d39b8c68e6f41ca8e73089ab997924d53d9d","last_reissued_at":"2026-05-17T23:57:31.895745Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:31.895745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.11074","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJY4u1fxkNMM3opui1YxUAFHqAJjmOyAY/s4Qn3REyoLaWLMh7Rx6NdJT69FbXU6iG7vYgujhuEMK+vI66BXDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T05:04:24.077928Z"},"content_sha256":"de7ea2f14f1232ab70d44c0eb49d4ce523e98616ac46dfba6b6ef191e01dedf0","schema_version":"1.0","event_id":"sha256:de7ea2f14f1232ab70d44c0eb49d4ce523e98616ac46dfba6b6ef191e01dedf0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OY6UIUB3I5I3RU2N7ZVQQZOTTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Tessler, Daniel J. Mankowitz, Shie Mannor","submitted_at":"2018-05-28T17:31:11Z","abstract_excerpt":"Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general constraints. In this work we present a novel multi-timescale approach for constrained policy optimization, called `Reward Constrained Policy Optimization' (RCPO), which uses an alternative penalty signal to guide the policy towards a constraint satisfying one. We prove the converge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11074","kind":"arxiv","version":3},"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":"2026-05-17T23:57:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gC3DdKHNIb03L+0Dqa3jggTfjN+ScqQGhec9lfFMk8DPT2eZSQ7W+ZNRvlHuWHmdsyN67CgAJm8c3TROrc/eDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T05:04:24.078276Z"},"content_sha256":"9bb9cbab6a88f985c0de276e5ed3bb5b0de38f0f657b060347c5d9c13781ce48","schema_version":"1.0","event_id":"sha256:9bb9cbab6a88f985c0de276e5ed3bb5b0de38f0f657b060347c5d9c13781ce48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/bundle.json","state_url":"https://pith.science/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/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":"2026-05-21T05:04:24Z","links":{"resolver":"https://pith.science/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO","bundle":"https://pith.science/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/bundle.json","state":"https://pith.science/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OY6UIUB3I5I3RU2N7ZVQQZOTTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OY6UIUB3I5I3RU2N7ZVQQZOTTO","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":"e8c4da5368282395e3a8694b960f3bfa5251ba844a65fe5e68c2005f31c6d322","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:31:11Z","title_canon_sha256":"6ad4503a61e54aa72d763a4654ce6df6dbdae9b9f11d9fdc8100fb581baa447a"},"schema_version":"1.0","source":{"id":"1805.11074","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.11074","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"arxiv_version","alias_value":"1805.11074v3","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11074","created_at":"2026-05-17T23:57:31Z"},{"alias_kind":"pith_short_12","alias_value":"OY6UIUB3I5I3","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OY6UIUB3I5I3RU2N","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OY6UIUB3","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:9bb9cbab6a88f985c0de276e5ed3bb5b0de38f0f657b060347c5d9c13781ce48","target":"graph","created_at":"2026-05-17T23:57:31Z","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":"Solving tasks in Reinforcement Learning is no easy feat. As the goal of the agent is to maximize the accumulated reward, it often learns to exploit loopholes and misspecifications in the reward signal resulting in unwanted behavior. While constraints may solve this issue, there is no closed form solution for general constraints. In this work we present a novel multi-timescale approach for constrained policy optimization, called `Reward Constrained Policy Optimization' (RCPO), which uses an alternative penalty signal to guide the policy towards a constraint satisfying one. We prove the converge","authors_text":"Chen Tessler, Daniel J. Mankowitz, Shie Mannor","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:31:11Z","title":"Reward Constrained Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11074","kind":"arxiv","version":3},"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:de7ea2f14f1232ab70d44c0eb49d4ce523e98616ac46dfba6b6ef191e01dedf0","target":"record","created_at":"2026-05-17T23:57:31Z","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":"e8c4da5368282395e3a8694b960f3bfa5251ba844a65fe5e68c2005f31c6d322","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-28T17:31:11Z","title_canon_sha256":"6ad4503a61e54aa72d763a4654ce6df6dbdae9b9f11d9fdc8100fb581baa447a"},"schema_version":"1.0","source":{"id":"1805.11074","kind":"arxiv","version":3}},"canonical_sha256":"763d44503b4751b8d34dfe6b0865d39b8c68e6f41ca8e73089ab997924d53d9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"763d44503b4751b8d34dfe6b0865d39b8c68e6f41ca8e73089ab997924d53d9d","first_computed_at":"2026-05-17T23:57:31.895745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:31.895745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DnV0aGSk8yWGXUvEfa80jXX9kd6mHtRegM4R0N6wi3IBy410y2DtT6LlWwuxxGjqZ1m+Wc2pco8QkE33GXy1Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:31.896191Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.11074","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de7ea2f14f1232ab70d44c0eb49d4ce523e98616ac46dfba6b6ef191e01dedf0","sha256:9bb9cbab6a88f985c0de276e5ed3bb5b0de38f0f657b060347c5d9c13781ce48"],"state_sha256":"4ff958d9250e67960320da642aa1611bb22327ff4d5e2955238dadb5f995a1b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EO8Rvooscvg5i3syBcblDLNEjnNOj7saEofVkeLQC2VxRDC6CAw5OeNwFL9QVf7PqyIPZZ2lJjtdfsjuMhoACQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T05:04:24.080363Z","bundle_sha256":"531f06d73359a57e554972d4a6fd0b474c8d254eced8ef3e68380023393e644b"}}