{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:Z4OP3KWE4E6MUJTBNX56HTEBR5","short_pith_number":"pith:Z4OP3KWE","canonical_record":{"source":{"id":"2211.13257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T19:09:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c78c485242b780059e37c3c3c539d3a4df921be4ad1b7c19fd51398fbdb2c7f","abstract_canon_sha256":"aaf38ef3cc649088e86ed8af6e125493b23776ee7a7a8192b22abfa4fff492bc"},"schema_version":"1.0"},"canonical_sha256":"cf1cfdaac4e13cca26616dfbe3cc818f54b5625f92421f3757bbffb5aabd5a22","source":{"kind":"arxiv","id":"2211.13257","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13257","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13257v1","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13257","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z4OP3KWE4E6M","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z4OP3KWE4E6MUJTB","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z4OP3KWE","created_at":"2026-07-05T05:19:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:Z4OP3KWE4E6MUJTBNX56HTEBR5","target":"record","payload":{"canonical_record":{"source":{"id":"2211.13257","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T19:09:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9c78c485242b780059e37c3c3c539d3a4df921be4ad1b7c19fd51398fbdb2c7f","abstract_canon_sha256":"aaf38ef3cc649088e86ed8af6e125493b23776ee7a7a8192b22abfa4fff492bc"},"schema_version":"1.0"},"canonical_sha256":"cf1cfdaac4e13cca26616dfbe3cc818f54b5625f92421f3757bbffb5aabd5a22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:01.834711Z","signature_b64":"f0AY0adCF1xExhHqsKoaGlntSBM8LxtuL5QGzu/MrYuzPaXgrbI4xodrAqWPuhtx9x3L+DcjTVg7k51S9IoyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf1cfdaac4e13cca26616dfbe3cc818f54b5625f92421f3757bbffb5aabd5a22","last_reissued_at":"2026-07-05T05:19:01.831973Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:01.831973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.13257","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":"2026-07-05T05:19:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGckazbeglEkB/wJzrrxMV7ENQ78VTKij5Pewel4+e6XQwPurQgNedh622/aeQQwcZNqsdW/OJLNhuh8xTubDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:22:16.978560Z"},"content_sha256":"25141aa334274806b04a6537ef75b74cb923c9506ac16cf31cc6493121156381","schema_version":"1.0","event_id":"sha256:25141aa334274806b04a6537ef75b74cb923c9506ac16cf31cc6493121156381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:Z4OP3KWE4E6MUJTBNX56HTEBR5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gang Niub, Masashi Sugiyama, Tingting Zhao, Wei Sun, Yarui Chen, Ying Wang","submitted_at":"2022-11-23T19:09:37Z","abstract_excerpt":"Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL, as a class of efficient DRL methods, performs the learning of state representations simultaneously with policy learning in an end-to-end manner when facing large-scale continuous state and action spaces. However, training such a large policy model requires a large number of trajectory samples and training time. On the other hand, the learned policy often fai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13257","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.13257/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T05:19:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1LQkvsS6wOyd76xrZfRy3h7UT4mRR15C9RLCeTfWHWaO7opBNanMXNmirmmBjCHJykaMJzA2k2YLxNvjI6HBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T16:22:16.979080Z"},"content_sha256":"dfffcea093a9d040dd63888f47919ca501fc85576d6b5210637de5d071ba7c74","schema_version":"1.0","event_id":"sha256:dfffcea093a9d040dd63888f47919ca501fc85576d6b5210637de5d071ba7c74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/bundle.json","state_url":"https://pith.science/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/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":"2026-08-23T16:22:16Z","links":{"resolver":"https://pith.science/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5","bundle":"https://pith.science/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/bundle.json","state":"https://pith.science/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4OP3KWE4E6MUJTBNX56HTEBR5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:Z4OP3KWE4E6MUJTBNX56HTEBR5","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":"aaf38ef3cc649088e86ed8af6e125493b23776ee7a7a8192b22abfa4fff492bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T19:09:37Z","title_canon_sha256":"9c78c485242b780059e37c3c3c539d3a4df921be4ad1b7c19fd51398fbdb2c7f"},"schema_version":"1.0","source":{"id":"2211.13257","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13257","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13257v1","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13257","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z4OP3KWE4E6M","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z4OP3KWE4E6MUJTB","created_at":"2026-07-05T05:19:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z4OP3KWE","created_at":"2026-07-05T05:19:01Z"}],"graph_snapshots":[{"event_id":"sha256:dfffcea093a9d040dd63888f47919ca501fc85576d6b5210637de5d071ba7c74","target":"graph","created_at":"2026-07-05T05:19:01Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.13257/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL, as a class of efficient DRL methods, performs the learning of state representations simultaneously with policy learning in an end-to-end manner when facing large-scale continuous state and action spaces. However, training such a large policy model requires a large number of trajectory samples and training time. On the other hand, the learned policy often fai","authors_text":"Gang Niub, Masashi Sugiyama, Tingting Zhao, Wei Sun, Yarui Chen, Ying Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T19:09:37Z","title":"Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13257","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":"sha256:25141aa334274806b04a6537ef75b74cb923c9506ac16cf31cc6493121156381","target":"record","created_at":"2026-07-05T05:19:01Z","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":"aaf38ef3cc649088e86ed8af6e125493b23776ee7a7a8192b22abfa4fff492bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-23T19:09:37Z","title_canon_sha256":"9c78c485242b780059e37c3c3c539d3a4df921be4ad1b7c19fd51398fbdb2c7f"},"schema_version":"1.0","source":{"id":"2211.13257","kind":"arxiv","version":1}},"canonical_sha256":"cf1cfdaac4e13cca26616dfbe3cc818f54b5625f92421f3757bbffb5aabd5a22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf1cfdaac4e13cca26616dfbe3cc818f54b5625f92421f3757bbffb5aabd5a22","first_computed_at":"2026-07-05T05:19:01.831973Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:01.831973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f0AY0adCF1xExhHqsKoaGlntSBM8LxtuL5QGzu/MrYuzPaXgrbI4xodrAqWPuhtx9x3L+DcjTVg7k51S9IoyAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:01.834711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13257","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25141aa334274806b04a6537ef75b74cb923c9506ac16cf31cc6493121156381","sha256:dfffcea093a9d040dd63888f47919ca501fc85576d6b5210637de5d071ba7c74"],"state_sha256":"3828752ab3adb53825ce06bed2c4d3ecfe48aa8d345ef86e44f3d0b53c7c44d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cx0Mx92Vp5VNP2m1WHCox8SOHr2kcSNgJxySL7BBS9Ysdu8AZXBugpL+GZcMSeyxGq0bla6yBPhjQVR4OYk0Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T16:22:16.984387Z","bundle_sha256":"90e7ee36737ee2faad7b78a1fb876925b26918a0bc54a414fdc39f8d6049dfb1"}}