{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RR3KJX5EHOKXHG6CFCLX3DK6B6","short_pith_number":"pith:RR3KJX5E","canonical_record":{"source":{"id":"1812.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T22:29:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c9010c7bfdd345a3b5fbf1756eb3861526c2b8ceb205f59246cff861b004baf","abstract_canon_sha256":"5a2caaf670d49565c78d74399555889dccd1256ce3e96cd9cae0434103e79a6f"},"schema_version":"1.0"},"canonical_sha256":"8c76a4dfa43b95739bc228977d8d5e0fa2c36d039105fd0fcd2af18b070f064f","source":{"kind":"arxiv","id":"1812.02256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02256","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02256v1","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02256","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"RR3KJX5EHOKX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RR3KJX5EHOKXHG6C","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RR3KJX5E","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RR3KJX5EHOKXHG6CFCLX3DK6B6","target":"record","payload":{"canonical_record":{"source":{"id":"1812.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T22:29:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c9010c7bfdd345a3b5fbf1756eb3861526c2b8ceb205f59246cff861b004baf","abstract_canon_sha256":"5a2caaf670d49565c78d74399555889dccd1256ce3e96cd9cae0434103e79a6f"},"schema_version":"1.0"},"canonical_sha256":"8c76a4dfa43b95739bc228977d8d5e0fa2c36d039105fd0fcd2af18b070f064f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:56.755183Z","signature_b64":"wxXZi9GZQML1/oMEDzxcqK2FAffokfVqT/nzDv9E8vYc9+Rs971DuyGxRAXfMEr4mbj6UkrRVpTuICURNFHWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c76a4dfa43b95739bc228977d8d5e0fa2c36d039105fd0fcd2af18b070f064f","last_reissued_at":"2026-05-17T23:58:56.754598Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:56.754598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.02256","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":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6FFUXuaZ1LEcJ8+AB9fi/2auO+AzDH54cwFmP7vxoBVz4l3b1nF11MH0ZyCHnj5tud6pgxXRcAS6pG20q3HuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:43:35.043818Z"},"content_sha256":"7bde75466850adfad907b50f01b824a11db9e792068486fa82419a3c2ac2c5cd","schema_version":"1.0","event_id":"sha256:7bde75466850adfad907b50f01b824a11db9e792068486fa82419a3c2ac2c5cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RR3KJX5EHOKXHG6CFCLX3DK6B6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Relative Entropy Regularized Policy Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abbas Abdolmaleki, Dan Belov, Jonas Degrave, Jost Tobias Springenberg, Martin Riedmiller, Nicolas Heess, Steven Bohez, Yuval Tassa","submitted_at":"2018-12-05T22:29:11Z","abstract_excerpt":"We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function; ii) policy improvement via the estimation of a local non-parametric policy; and iii) generalization by fitting a parametric policy. Each step can be implemented in different ways, giving rise to several algorithm variants. Our algorithm draws on connections to existing literatur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02256","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":"2026-05-17T23:58:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lv+wnXqOD76wPmNiW3QpfQMgM9q4eZwW5P75JKFb4apbt/L3R2pN7iLkUrCdMuFJYiHaWOcBLt31/fRZy7lrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T05:43:35.044482Z"},"content_sha256":"c7ebf6f8e09a5cbdd9cdf2234de38041555d8eb2d154e946a407428c353e81c6","schema_version":"1.0","event_id":"sha256:c7ebf6f8e09a5cbdd9cdf2234de38041555d8eb2d154e946a407428c353e81c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/bundle.json","state_url":"https://pith.science/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/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":"2026-06-09T05:43:35Z","links":{"resolver":"https://pith.science/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6","bundle":"https://pith.science/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/bundle.json","state":"https://pith.science/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RR3KJX5EHOKXHG6CFCLX3DK6B6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RR3KJX5EHOKXHG6CFCLX3DK6B6","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":"5a2caaf670d49565c78d74399555889dccd1256ce3e96cd9cae0434103e79a6f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T22:29:11Z","title_canon_sha256":"3c9010c7bfdd345a3b5fbf1756eb3861526c2b8ceb205f59246cff861b004baf"},"schema_version":"1.0","source":{"id":"1812.02256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.02256","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"arxiv_version","alias_value":"1812.02256v1","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02256","created_at":"2026-05-17T23:58:56Z"},{"alias_kind":"pith_short_12","alias_value":"RR3KJX5EHOKX","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RR3KJX5EHOKXHG6C","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RR3KJX5E","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:c7ebf6f8e09a5cbdd9cdf2234de38041555d8eb2d154e946a407428c353e81c6","target":"graph","created_at":"2026-05-17T23:58:56Z","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":"We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function; ii) policy improvement via the estimation of a local non-parametric policy; and iii) generalization by fitting a parametric policy. Each step can be implemented in different ways, giving rise to several algorithm variants. Our algorithm draws on connections to existing literatur","authors_text":"Abbas Abdolmaleki, Dan Belov, Jonas Degrave, Jost Tobias Springenberg, Martin Riedmiller, Nicolas Heess, Steven Bohez, Yuval Tassa","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T22:29:11Z","title":"Relative Entropy Regularized Policy Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02256","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":"sha256:7bde75466850adfad907b50f01b824a11db9e792068486fa82419a3c2ac2c5cd","target":"record","created_at":"2026-05-17T23:58:56Z","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":"5a2caaf670d49565c78d74399555889dccd1256ce3e96cd9cae0434103e79a6f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-05T22:29:11Z","title_canon_sha256":"3c9010c7bfdd345a3b5fbf1756eb3861526c2b8ceb205f59246cff861b004baf"},"schema_version":"1.0","source":{"id":"1812.02256","kind":"arxiv","version":1}},"canonical_sha256":"8c76a4dfa43b95739bc228977d8d5e0fa2c36d039105fd0fcd2af18b070f064f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c76a4dfa43b95739bc228977d8d5e0fa2c36d039105fd0fcd2af18b070f064f","first_computed_at":"2026-05-17T23:58:56.754598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:56.754598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wxXZi9GZQML1/oMEDzxcqK2FAffokfVqT/nzDv9E8vYc9+Rs971DuyGxRAXfMEr4mbj6UkrRVpTuICURNFHWAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:56.755183Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.02256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bde75466850adfad907b50f01b824a11db9e792068486fa82419a3c2ac2c5cd","sha256:c7ebf6f8e09a5cbdd9cdf2234de38041555d8eb2d154e946a407428c353e81c6"],"state_sha256":"eac1ce494632cdbe1f49a8fa7fd61c4141fef1e0471698737776535b6371e434"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k9k/WUjibBjPCSW8AClGfNL+tbgNrddu4ZFVXotHvKEZyyaDHNW6kzpyQjE4ZWLI7ubSEHCdGS/cFgB8px7XBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T05:43:35.048590Z","bundle_sha256":"9f83dff90d0890ca58e66e924782d445154c026fb24448576bfbb29b8cb56538"}}