{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YGIIMECZTUIS4O5A2VDDVPHQSZ","short_pith_number":"pith:YGIIMECZ","canonical_record":{"source":{"id":"1803.05044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T21:04:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb91a267c81d6e4b735792ff3795e8a09ec78b74b83d15a798efe5bcbd4dce23","abstract_canon_sha256":"045fa074946c0a554cbcf8a71e5e2c210314344277c3e6fa9a14c1412b364a4a"},"schema_version":"1.0"},"canonical_sha256":"c1908610599d112e3ba0d5463abcf09640c482b15671b50cfba9aad241641eb6","source":{"kind":"arxiv","id":"1803.05044","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.05044","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.05044v2","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05044","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"YGIIMECZTUIS","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YGIIMECZTUIS4O5A","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YGIIMECZ","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YGIIMECZTUIS4O5A2VDDVPHQSZ","target":"record","payload":{"canonical_record":{"source":{"id":"1803.05044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T21:04:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb91a267c81d6e4b735792ff3795e8a09ec78b74b83d15a798efe5bcbd4dce23","abstract_canon_sha256":"045fa074946c0a554cbcf8a71e5e2c210314344277c3e6fa9a14c1412b364a4a"},"schema_version":"1.0"},"canonical_sha256":"c1908610599d112e3ba0d5463abcf09640c482b15671b50cfba9aad241641eb6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:20:13.435399Z","signature_b64":"XoaPzvhIbmIQcDPaQ/3Smx/IUZ2ViqiPnDepBhff5Kw8ggmuNiZzjErtLgma5sonkuk2TyWNbxOMYCptmmtWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1908610599d112e3ba0d5463abcf09640c482b15671b50cfba9aad241641eb6","last_reissued_at":"2026-05-18T00:20:13.434977Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:20:13.434977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.05044","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7e54sT/52M+DhUfbfKilD4M6DRGwLXvQ3hs1pNiVoln/brw/Fv/Iy8UX66mKOep3VsX2A19PiW4b3J+3O3QAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:13:37.732796Z"},"content_sha256":"2ac831f953df7547e255f288043ff563d72d3b33c30ef6204316e15cb073f272","schema_version":"1.0","event_id":"sha256:2ac831f953df7547e255f288043ff563d72d3b33c30ef6204316e15cb073f272"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YGIIMECZTUIS4O5A2VDDVPHQSZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Explore with Meta-Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Liang Zhao, Qiang Liu, Tianbing Xu","submitted_at":"2018-03-13T21:04:17Z","abstract_excerpt":"The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existing exploration methods are mostly based on adding noise to the on-going actor policy and can only explore \\emph{local} regions close to what the actor policy dictates. In this work, we develop a simple meta-policy gradient algorithm that allows us to adaptively learn the exploration policy in DDPG. Our algorithm allows us to train flexible exploration behaviors that are independent of the actor policy, yielding a \\emp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05044","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":"2026-05-18T00:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2BGGCZwoNipdgCUzySpTfhxkJMJ/3PrKK+bVM7J8nNfHAyGlviynPTtto/MEaAvbK3ZQtc37nqvugRvbI3kRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:13:37.733460Z"},"content_sha256":"dae21bb4b5d0594a049f93e696ef79a4c6c58b02e78904c3ccf7c7a3a91b8106","schema_version":"1.0","event_id":"sha256:dae21bb4b5d0594a049f93e696ef79a4c6c58b02e78904c3ccf7c7a3a91b8106"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/bundle.json","state_url":"https://pith.science/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/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":"2026-05-30T16:13:37Z","links":{"resolver":"https://pith.science/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ","bundle":"https://pith.science/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/bundle.json","state":"https://pith.science/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGIIMECZTUIS4O5A2VDDVPHQSZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YGIIMECZTUIS4O5A2VDDVPHQSZ","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":"045fa074946c0a554cbcf8a71e5e2c210314344277c3e6fa9a14c1412b364a4a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T21:04:17Z","title_canon_sha256":"bb91a267c81d6e4b735792ff3795e8a09ec78b74b83d15a798efe5bcbd4dce23"},"schema_version":"1.0","source":{"id":"1803.05044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.05044","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"1803.05044v2","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.05044","created_at":"2026-05-18T00:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"YGIIMECZTUIS","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YGIIMECZTUIS4O5A","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YGIIMECZ","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:dae21bb4b5d0594a049f93e696ef79a4c6c58b02e78904c3ccf7c7a3a91b8106","target":"graph","created_at":"2026-05-18T00:20:13Z","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":"The performance of off-policy learning, including deep Q-learning and deep deterministic policy gradient (DDPG), critically depends on the choice of the exploration policy. Existing exploration methods are mostly based on adding noise to the on-going actor policy and can only explore \\emph{local} regions close to what the actor policy dictates. In this work, we develop a simple meta-policy gradient algorithm that allows us to adaptively learn the exploration policy in DDPG. Our algorithm allows us to train flexible exploration behaviors that are independent of the actor policy, yielding a \\emp","authors_text":"Jian Peng, Liang Zhao, Qiang Liu, Tianbing Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T21:04:17Z","title":"Learning to Explore with Meta-Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.05044","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":"sha256:2ac831f953df7547e255f288043ff563d72d3b33c30ef6204316e15cb073f272","target":"record","created_at":"2026-05-18T00:20:13Z","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":"045fa074946c0a554cbcf8a71e5e2c210314344277c3e6fa9a14c1412b364a4a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-13T21:04:17Z","title_canon_sha256":"bb91a267c81d6e4b735792ff3795e8a09ec78b74b83d15a798efe5bcbd4dce23"},"schema_version":"1.0","source":{"id":"1803.05044","kind":"arxiv","version":2}},"canonical_sha256":"c1908610599d112e3ba0d5463abcf09640c482b15671b50cfba9aad241641eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1908610599d112e3ba0d5463abcf09640c482b15671b50cfba9aad241641eb6","first_computed_at":"2026-05-18T00:20:13.434977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:20:13.434977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XoaPzvhIbmIQcDPaQ/3Smx/IUZ2ViqiPnDepBhff5Kw8ggmuNiZzjErtLgma5sonkuk2TyWNbxOMYCptmmtWCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:20:13.435399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.05044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ac831f953df7547e255f288043ff563d72d3b33c30ef6204316e15cb073f272","sha256:dae21bb4b5d0594a049f93e696ef79a4c6c58b02e78904c3ccf7c7a3a91b8106"],"state_sha256":"6ae0b792b1365afc7f06532c613215f39823262e6205469efd2dc95e9a06e3bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eFHyrVW3R5P8gby94azCHgc2HK6uKYk4lDf9p63CUjO91OTw8adEu5U6eKUa54WMCqaJnYTamtFp0uPF1RJeBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:13:37.736963Z","bundle_sha256":"99c06e195700f4dbef15fd046e44130be91c75c301bc2f824d1a263dbc3c0301"}}