{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XSWSRNMHYUZNO6MG6FFOH3LNQD","short_pith_number":"pith:XSWSRNMH","canonical_record":{"source":{"id":"1903.07765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T23:35:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"917ad303a01648757570100f6e8d29cd76b95768ec321e1defbf92eebae2e260","abstract_canon_sha256":"9108f202fbb81b0ac877fafd10a254c08ce8b068bf65eb7eacd1eae20a79aa60"},"schema_version":"1.0"},"canonical_sha256":"bcad28b587c532d77986f14ae3ed6d80db1d2eb0f5658b776e97351ed5112880","source":{"kind":"arxiv","id":"1903.07765","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07765","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07765v3","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07765","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"XSWSRNMHYUZN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XSWSRNMHYUZNO6MG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XSWSRNMH","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XSWSRNMHYUZNO6MG6FFOH3LNQD","target":"record","payload":{"canonical_record":{"source":{"id":"1903.07765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T23:35:23Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"917ad303a01648757570100f6e8d29cd76b95768ec321e1defbf92eebae2e260","abstract_canon_sha256":"9108f202fbb81b0ac877fafd10a254c08ce8b068bf65eb7eacd1eae20a79aa60"},"schema_version":"1.0"},"canonical_sha256":"bcad28b587c532d77986f14ae3ed6d80db1d2eb0f5658b776e97351ed5112880","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:40.915106Z","signature_b64":"5X8yRKzSPt1Oh+nwEGlzMz2usNZv35LKGRKxIduPS8kyx5CnD6jdtjaCJOwnDn7uasXARUu6oVWgda1GQOBZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcad28b587c532d77986f14ae3ed6d80db1d2eb0f5658b776e97351ed5112880","last_reissued_at":"2026-05-17T23:46:40.914438Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:40.914438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.07765","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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAU5zZmYNB1MR46Hm/FhHMZ+J6sIC3tdgZB2tMuvdogFxb+8+ON/Sfq5t8ag+TGxH6ZPL/QrcFeQcxgK5H5TDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:35:54.274399Z"},"content_sha256":"d6a0740d7b674816f4734298d6995629107063a77fda210cffe6dc582398a44b","schema_version":"1.0","event_id":"sha256:d6a0740d7b674816f4734298d6995629107063a77fda210cffe6dc582398a44b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XSWSRNMHYUZNO6MG6FFOH3LNQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning with Decorrelation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Borislav Mavrin, Hengshuai Yao, Linglong Kong","submitted_at":"2019-03-18T23:35:23Z","abstract_excerpt":"Learning an effective representation for high-dimensional data is a challenging problem in reinforcement learning (RL). Deep reinforcement learning (DRL) such as Deep Q networks (DQN) achieves remarkable success in computer games by learning deeply encoded representation from convolution networks. In this paper, we propose a simple yet very effective method for representation learning with DRL algorithms. Our key insight is that features learned by DRL algorithms are highly correlated, which interferes with learning. By adding a regularized loss that penalizes correlation in latent features (w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07765","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":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tdBmd+u3ebRcqTlabMFAVvY+EQNiLc1EDtvIlKKnQqRhncwKdYqC/H9Ox4DtqqgVGquPW+Go2TSidP4hMJ3BAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:35:54.275501Z"},"content_sha256":"4fb2114f75e62d7e67dd3148987efd01fbde8504fef6b48963ec0d645428d082","schema_version":"1.0","event_id":"sha256:4fb2114f75e62d7e67dd3148987efd01fbde8504fef6b48963ec0d645428d082"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/bundle.json","state_url":"https://pith.science/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/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":"2026-08-15T16:35:54Z","links":{"resolver":"https://pith.science/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD","bundle":"https://pith.science/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/bundle.json","state":"https://pith.science/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XSWSRNMHYUZNO6MG6FFOH3LNQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XSWSRNMHYUZNO6MG6FFOH3LNQD","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":"9108f202fbb81b0ac877fafd10a254c08ce8b068bf65eb7eacd1eae20a79aa60","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T23:35:23Z","title_canon_sha256":"917ad303a01648757570100f6e8d29cd76b95768ec321e1defbf92eebae2e260"},"schema_version":"1.0","source":{"id":"1903.07765","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.07765","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.07765v3","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07765","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"XSWSRNMHYUZN","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XSWSRNMHYUZNO6MG","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XSWSRNMH","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:4fb2114f75e62d7e67dd3148987efd01fbde8504fef6b48963ec0d645428d082","target":"graph","created_at":"2026-05-17T23:46:40Z","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":"Learning an effective representation for high-dimensional data is a challenging problem in reinforcement learning (RL). Deep reinforcement learning (DRL) such as Deep Q networks (DQN) achieves remarkable success in computer games by learning deeply encoded representation from convolution networks. In this paper, we propose a simple yet very effective method for representation learning with DRL algorithms. Our key insight is that features learned by DRL algorithms are highly correlated, which interferes with learning. By adding a regularized loss that penalizes correlation in latent features (w","authors_text":"Borislav Mavrin, Hengshuai Yao, Linglong Kong","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T23:35:23Z","title":"Deep Reinforcement Learning with Decorrelation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07765","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:d6a0740d7b674816f4734298d6995629107063a77fda210cffe6dc582398a44b","target":"record","created_at":"2026-05-17T23:46:40Z","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":"9108f202fbb81b0ac877fafd10a254c08ce8b068bf65eb7eacd1eae20a79aa60","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-18T23:35:23Z","title_canon_sha256":"917ad303a01648757570100f6e8d29cd76b95768ec321e1defbf92eebae2e260"},"schema_version":"1.0","source":{"id":"1903.07765","kind":"arxiv","version":3}},"canonical_sha256":"bcad28b587c532d77986f14ae3ed6d80db1d2eb0f5658b776e97351ed5112880","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bcad28b587c532d77986f14ae3ed6d80db1d2eb0f5658b776e97351ed5112880","first_computed_at":"2026-05-17T23:46:40.914438Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:40.914438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5X8yRKzSPt1Oh+nwEGlzMz2usNZv35LKGRKxIduPS8kyx5CnD6jdtjaCJOwnDn7uasXARUu6oVWgda1GQOBZBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:40.915106Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.07765","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6a0740d7b674816f4734298d6995629107063a77fda210cffe6dc582398a44b","sha256:4fb2114f75e62d7e67dd3148987efd01fbde8504fef6b48963ec0d645428d082"],"state_sha256":"d5837bfe0594c9ba8d195b2f1b150c1e938fb23a3c8d8087b17e7bec2fb30e5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Krguzt5tt67/09b7A1dUhUcP19c10W1YUmyAAjCqxzSUDtbue/zi4/tR9ruNI+Wk7b+UtXInzmNFkwfMxAYZDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:35:54.282170Z","bundle_sha256":"1a8d26b95c31b2ee6b99cbb12787752299016b700b03be6a696d5279376be235"}}