{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VIGWOYVJPRCMGWT3P3D4IAVSO7","short_pith_number":"pith:VIGWOYVJ","canonical_record":{"source":{"id":"1806.06798","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-10T08:24:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c6009bdeb541e2675bf3c1731949037337be02c64946d3285adb92a26f690063","abstract_canon_sha256":"8d34b8dbd298dba73f4af8215bdd37275e6ee8fc85ea9cc03198d86d17b3de86"},"schema_version":"1.0"},"canonical_sha256":"aa0d6762a97c44c35a7b7ec7c402b277dbb3b962b13d45a60e2c89ece579134e","source":{"kind":"arxiv","id":"1806.06798","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06798","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06798v2","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06798","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"pith_short_12","alias_value":"VIGWOYVJPRCM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VIGWOYVJPRCMGWT3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VIGWOYVJ","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VIGWOYVJPRCMGWT3P3D4IAVSO7","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06798","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-10T08:24:36Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"c6009bdeb541e2675bf3c1731949037337be02c64946d3285adb92a26f690063","abstract_canon_sha256":"8d34b8dbd298dba73f4af8215bdd37275e6ee8fc85ea9cc03198d86d17b3de86"},"schema_version":"1.0"},"canonical_sha256":"aa0d6762a97c44c35a7b7ec7c402b277dbb3b962b13d45a60e2c89ece579134e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:54.185857Z","signature_b64":"Y0rLGQP8ZTOlQAFpH8nIJ/kZjw0YeSqwSmFydujnFG/Gnj2iXI/nbieX3Zta2fcj/oApCcmzglszEakYpo7ZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa0d6762a97c44c35a7b7ec7c402b277dbb3b962b13d45a60e2c89ece579134e","last_reissued_at":"2026-05-17T23:54:54.185336Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:54.185336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06798","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":"2026-05-17T23:54:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HG85kRXTC6HBKDLAdro1mTBTZ2rSz+zCeCJGOpNxntTXPt7eatlpby1Shv6mSvFz7W1qrGfX2HlRM2pi+upDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:35:39.042016Z"},"content_sha256":"15896f792d72ee5a0fedaf8cd738fd0b104ea13d3ea11bffcccddc8ec4abcf08","schema_version":"1.0","event_id":"sha256:15896f792d72ee5a0fedaf8cd738fd0b104ea13d3ea11bffcccddc8ec4abcf08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VIGWOYVJPRCMGWT3P3D4IAVSO7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Policy for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shipra Agrawal, Yunhao Tang","submitted_at":"2018-06-10T08:24:36Z","abstract_excerpt":"We introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization combined with a rich policy class can attain desirable properties displayed under maximum entropy reinforcement learning framework, such as robustness and multi-modality."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06798","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":""},"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":"2026-05-17T23:54:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N03HcPTdG+0JD/tBtTw8b+N66Snute4lQMioHWmpwxQqH7pQM91OdDTxjwgJ8oj60y/UG3GHg+NQwLlPxk+pDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:35:39.042729Z"},"content_sha256":"1cd931a07145cd4ab5525cbd02ac279b64e83cf1e883633971ff04ca81856901","schema_version":"1.0","event_id":"sha256:1cd931a07145cd4ab5525cbd02ac279b64e83cf1e883633971ff04ca81856901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/bundle.json","state_url":"https://pith.science/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/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":"2026-06-10T09:35:39Z","links":{"resolver":"https://pith.science/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7","bundle":"https://pith.science/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/bundle.json","state":"https://pith.science/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIGWOYVJPRCMGWT3P3D4IAVSO7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VIGWOYVJPRCMGWT3P3D4IAVSO7","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":"8d34b8dbd298dba73f4af8215bdd37275e6ee8fc85ea9cc03198d86d17b3de86","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-10T08:24:36Z","title_canon_sha256":"c6009bdeb541e2675bf3c1731949037337be02c64946d3285adb92a26f690063"},"schema_version":"1.0","source":{"id":"1806.06798","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06798","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06798v2","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06798","created_at":"2026-05-17T23:54:54Z"},{"alias_kind":"pith_short_12","alias_value":"VIGWOYVJPRCM","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VIGWOYVJPRCMGWT3","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VIGWOYVJ","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:1cd931a07145cd4ab5525cbd02ac279b64e83cf1e883633971ff04ca81856901","target":"graph","created_at":"2026-05-17T23:54:54Z","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 introduce Implicit Policy, a general class of expressive policies that can flexibly represent complex action distributions in reinforcement learning, with efficient algorithms to compute entropy regularized policy gradients. We empirically show that, despite its simplicity in implementation, entropy regularization combined with a rich policy class can attain desirable properties displayed under maximum entropy reinforcement learning framework, such as robustness and multi-modality.","authors_text":"Shipra Agrawal, Yunhao Tang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-10T08:24:36Z","title":"Implicit Policy for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06798","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":"sha256:15896f792d72ee5a0fedaf8cd738fd0b104ea13d3ea11bffcccddc8ec4abcf08","target":"record","created_at":"2026-05-17T23:54:54Z","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":"8d34b8dbd298dba73f4af8215bdd37275e6ee8fc85ea9cc03198d86d17b3de86","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-10T08:24:36Z","title_canon_sha256":"c6009bdeb541e2675bf3c1731949037337be02c64946d3285adb92a26f690063"},"schema_version":"1.0","source":{"id":"1806.06798","kind":"arxiv","version":2}},"canonical_sha256":"aa0d6762a97c44c35a7b7ec7c402b277dbb3b962b13d45a60e2c89ece579134e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa0d6762a97c44c35a7b7ec7c402b277dbb3b962b13d45a60e2c89ece579134e","first_computed_at":"2026-05-17T23:54:54.185336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:54.185336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0rLGQP8ZTOlQAFpH8nIJ/kZjw0YeSqwSmFydujnFG/Gnj2iXI/nbieX3Zta2fcj/oApCcmzglszEakYpo7ZAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:54.185857Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06798","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15896f792d72ee5a0fedaf8cd738fd0b104ea13d3ea11bffcccddc8ec4abcf08","sha256:1cd931a07145cd4ab5525cbd02ac279b64e83cf1e883633971ff04ca81856901"],"state_sha256":"6d66929aad9d9f20f031acc881eeaa0f3ac5c3df5e00a579f2ac492971cc982d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fXZS74Qq7DUc0aQSdIzIBKY0Ja7Ja0tp+RRDa0zfsm/Q8W5PDy55KJ5jzKQsHIQ9NAY0u5jox5L4z6IdHY0yCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:35:39.046463Z","bundle_sha256":"263336416eb313e269eae3940b122b287985240489f40d17a69ca62620ab15f7"}}