{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PLTOGFIVIDT22IZ6HGF3PK2HGO","short_pith_number":"pith:PLTOGFIV","canonical_record":{"source":{"id":"2407.13755","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"996d29064fd603335ae6e630d13a3d7d5b7141410b43f0b01b580f2984843c44","abstract_canon_sha256":"c39e91bd1309971351cc60ee136e10f416710c4a5314dd61b7550a4d789a6037"},"schema_version":"1.0"},"canonical_sha256":"7ae6e3151540e7ad233e398bb7ab4733851124136ec7772bc9b88a480a25139c","source":{"kind":"arxiv","id":"2407.13755","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13755","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13755v3","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13755","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"PLTOGFIVIDT2","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"PLTOGFIVIDT22IZ6","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"PLTOGFIV","created_at":"2026-07-05T10:21:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PLTOGFIVIDT22IZ6HGF3PK2HGO","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13755","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:55:22Z","cross_cats_sorted":[],"title_canon_sha256":"996d29064fd603335ae6e630d13a3d7d5b7141410b43f0b01b580f2984843c44","abstract_canon_sha256":"c39e91bd1309971351cc60ee136e10f416710c4a5314dd61b7550a4d789a6037"},"schema_version":"1.0"},"canonical_sha256":"7ae6e3151540e7ad233e398bb7ab4733851124136ec7772bc9b88a480a25139c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:03.894383Z","signature_b64":"QLKS22bnsAEd7M1kjnnqlwCVlZPGTlqLAu0Ck3i9h5yKsrX9jZ0aWNit9Ts3xzx0fkscY0YV9vpPfyt+Vq4sAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ae6e3151540e7ad233e398bb7ab4733851124136ec7772bc9b88a480a25139c","last_reissued_at":"2026-07-05T10:21:03.893687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:03.893687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13755","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":"2026-07-05T10:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NmZyiY/hg70tTRZgTURFfTCMv7gH6kosg0gzVujogvac3N0TuGxUN+/Mu6+0XY+ZUkG/KUDBfWUO89O4UsjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:39:53.059058Z"},"content_sha256":"ed068775e053f41f4e14ea5d76f1f1c46eac75e3b29029b184b62d26dd637e20","schema_version":"1.0","event_id":"sha256:ed068775e053f41f4e14ea5d76f1f1c46eac75e3b29029b184b62d26dd637e20"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PLTOGFIVIDT22IZ6HGF3PK2HGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Random Latent Exploration for Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Ayush Sekhari, Pulkit Agrawal, Srinath Mahankali, Zhang-Wei Hong","submitted_at":"2024-07-18T17:55:22Z","abstract_excerpt":"We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which rewards the agent for attempting novel behaviors. The core idea of RLE is to encourage the agent to explore different parts of the environment by pursuing randomly sampled goals in a latent space. RLE is as simple as noise-based methods, as it avoids complex bonus calculations but retains the deep exploration benefits of bonus-based methods. Our experiments"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13755","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.13755/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":"2026-07-05T10:21:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3sKoncarJM63F90SKXRB4/8NrGoHPvTMX+tXZxlhUQml4WtvHcaqRFDPLzWSwM5nCnmsiJYAmJQAjpljC+0iDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:39:53.059435Z"},"content_sha256":"4d2d95a1ab8f0bddd343938fb9b8b6844747398dc173347c46639824918a369a","schema_version":"1.0","event_id":"sha256:4d2d95a1ab8f0bddd343938fb9b8b6844747398dc173347c46639824918a369a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/bundle.json","state_url":"https://pith.science/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/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":"2026-07-06T20:39:53Z","links":{"resolver":"https://pith.science/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO","bundle":"https://pith.science/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/bundle.json","state":"https://pith.science/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PLTOGFIVIDT22IZ6HGF3PK2HGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PLTOGFIVIDT22IZ6HGF3PK2HGO","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":"c39e91bd1309971351cc60ee136e10f416710c4a5314dd61b7550a4d789a6037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:55:22Z","title_canon_sha256":"996d29064fd603335ae6e630d13a3d7d5b7141410b43f0b01b580f2984843c44"},"schema_version":"1.0","source":{"id":"2407.13755","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13755","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13755v3","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13755","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_12","alias_value":"PLTOGFIVIDT2","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_16","alias_value":"PLTOGFIVIDT22IZ6","created_at":"2026-07-05T10:21:03Z"},{"alias_kind":"pith_short_8","alias_value":"PLTOGFIV","created_at":"2026-07-05T10:21:03Z"}],"graph_snapshots":[{"event_id":"sha256:4d2d95a1ab8f0bddd343938fb9b8b6844747398dc173347c46639824918a369a","target":"graph","created_at":"2026-07-05T10:21:03Z","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/2407.13755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Random Latent Exploration (RLE), a simple yet effective exploration strategy in reinforcement learning (RL). On average, RLE outperforms noise-based methods, which perturb the agent's actions, and bonus-based exploration, which rewards the agent for attempting novel behaviors. The core idea of RLE is to encourage the agent to explore different parts of the environment by pursuing randomly sampled goals in a latent space. RLE is as simple as noise-based methods, as it avoids complex bonus calculations but retains the deep exploration benefits of bonus-based methods. Our experiments","authors_text":"Alexander Rakhlin, Ayush Sekhari, Pulkit Agrawal, Srinath Mahankali, Zhang-Wei Hong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:55:22Z","title":"Random Latent Exploration for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13755","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:ed068775e053f41f4e14ea5d76f1f1c46eac75e3b29029b184b62d26dd637e20","target":"record","created_at":"2026-07-05T10:21:03Z","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":"c39e91bd1309971351cc60ee136e10f416710c4a5314dd61b7550a4d789a6037","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-18T17:55:22Z","title_canon_sha256":"996d29064fd603335ae6e630d13a3d7d5b7141410b43f0b01b580f2984843c44"},"schema_version":"1.0","source":{"id":"2407.13755","kind":"arxiv","version":3}},"canonical_sha256":"7ae6e3151540e7ad233e398bb7ab4733851124136ec7772bc9b88a480a25139c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ae6e3151540e7ad233e398bb7ab4733851124136ec7772bc9b88a480a25139c","first_computed_at":"2026-07-05T10:21:03.893687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:03.893687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QLKS22bnsAEd7M1kjnnqlwCVlZPGTlqLAu0Ck3i9h5yKsrX9jZ0aWNit9Ts3xzx0fkscY0YV9vpPfyt+Vq4sAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:03.894383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13755","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed068775e053f41f4e14ea5d76f1f1c46eac75e3b29029b184b62d26dd637e20","sha256:4d2d95a1ab8f0bddd343938fb9b8b6844747398dc173347c46639824918a369a"],"state_sha256":"6637902f8f317ea53b94fed4dd77142bc3560a2685f23e9fcfad314ae3c00564"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tKVCMeDTmF2FmN9gUGO17VeGWRsp+ILGHJFxmsYRrUi+/w2sBO3CVvhF69exwygFdY+xVwmN8c7N3VIr5FdLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:39:53.061240Z","bundle_sha256":"6a5f8dae71a5c6feae70ef86d19ecc24f41dece47ab5483b7d9130cb2fc34186"}}