{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TTJOULFN626M3VCAYXIJRXV2WT","short_pith_number":"pith:TTJOULFN","canonical_record":{"source":{"id":"2107.08966","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:31:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31186a9d8c5fd8f4cfefe600e52eb502533f8d9160d7a8e3fd135c9d2bef7989","abstract_canon_sha256":"ee6a9e69b8b7a079f6e72e8c11b82e38e69d1fbad2777bb6323b49b1d1bacd67"},"schema_version":"1.0"},"canonical_sha256":"9cd2ea2cadf6bccdd440c5d098debab4df3fba200035b89b527b85895a791f6d","source":{"kind":"arxiv","id":"2107.08966","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08966","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08966v3","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08966","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"TTJOULFN626M","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"TTJOULFN626M3VCA","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"TTJOULFN","created_at":"2026-07-05T03:55:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TTJOULFN626M3VCAYXIJRXV2WT","target":"record","payload":{"canonical_record":{"source":{"id":"2107.08966","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:31:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"31186a9d8c5fd8f4cfefe600e52eb502533f8d9160d7a8e3fd135c9d2bef7989","abstract_canon_sha256":"ee6a9e69b8b7a079f6e72e8c11b82e38e69d1fbad2777bb6323b49b1d1bacd67"},"schema_version":"1.0"},"canonical_sha256":"9cd2ea2cadf6bccdd440c5d098debab4df3fba200035b89b527b85895a791f6d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:55:28.623986Z","signature_b64":"AooxiXiLO64M65NcU4cF3Pix6UIykW6poXaI51hjf1fmgzD1hjhGldBv1g6CL9P2h/J08wt9XlkSrNJTzcPvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cd2ea2cadf6bccdd440c5d098debab4df3fba200035b89b527b85895a791f6d","last_reissued_at":"2026-07-05T03:55:28.623455Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:55:28.623455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.08966","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":"2026-07-05T03:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkS86l6hKeA8vwjWoDaEhOboO1gpkfkaGqTArgz7oGCKO6OEigTcmRFI86w3u23CeGsuYjN+IvvTxD+Ey1fECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:21:53.605260Z"},"content_sha256":"43d34ed2f0f6f6dd245e093c660fedbcecb42ea2637531c023e01b78948a7af0","schema_version":"1.0","event_id":"sha256:43d34ed2f0f6f6dd245e093c660fedbcecb42ea2637531c023e01b78948a7af0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TTJOULFN626M3VCAYXIJRXV2WT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Filippos Christianos, Josiah P. Hanna, Lukas Sch\\\"afer, Stefano V. Albrecht","submitted_at":"2021-07-19T15:31:02Z","abstract_excerpt":"Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work, we introduce Decoupled RL (DeRL) as a general framework which trains separate policies for intrinsically-motivated exploration and exploitation. Such decoupling allows DeRL to leverage the benefits of intrinsic rewards for exploration while demonstrating improved robustness and sample efficiency. We evaluate DeRL algorithms in two sparse-reward environments with multiple types"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08966","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/2107.08966/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":"2026-07-05T03:55:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U5b1vstvUDhJ755SZqyok7w3JnhIFxwpjfX98ucyRfVUXXob3HBZAbElVeZfAyJk3R9nefGxPdChu/dULtvgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:21:53.605770Z"},"content_sha256":"935a468b70802e924f8f6c748fc9c6ea95d02f29d9ff05a1617efebd290332e0","schema_version":"1.0","event_id":"sha256:935a468b70802e924f8f6c748fc9c6ea95d02f29d9ff05a1617efebd290332e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TTJOULFN626M3VCAYXIJRXV2WT/bundle.json","state_url":"https://pith.science/pith/TTJOULFN626M3VCAYXIJRXV2WT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TTJOULFN626M3VCAYXIJRXV2WT/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":"2026-07-31T16:21:53Z","links":{"resolver":"https://pith.science/pith/TTJOULFN626M3VCAYXIJRXV2WT","bundle":"https://pith.science/pith/TTJOULFN626M3VCAYXIJRXV2WT/bundle.json","state":"https://pith.science/pith/TTJOULFN626M3VCAYXIJRXV2WT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TTJOULFN626M3VCAYXIJRXV2WT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TTJOULFN626M3VCAYXIJRXV2WT","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":"ee6a9e69b8b7a079f6e72e8c11b82e38e69d1fbad2777bb6323b49b1d1bacd67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:31:02Z","title_canon_sha256":"31186a9d8c5fd8f4cfefe600e52eb502533f8d9160d7a8e3fd135c9d2bef7989"},"schema_version":"1.0","source":{"id":"2107.08966","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.08966","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"arxiv_version","alias_value":"2107.08966v3","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.08966","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_12","alias_value":"TTJOULFN626M","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_16","alias_value":"TTJOULFN626M3VCA","created_at":"2026-07-05T03:55:28Z"},{"alias_kind":"pith_short_8","alias_value":"TTJOULFN","created_at":"2026-07-05T03:55:28Z"}],"graph_snapshots":[{"event_id":"sha256:935a468b70802e924f8f6c748fc9c6ea95d02f29d9ff05a1617efebd290332e0","target":"graph","created_at":"2026-07-05T03:55:28Z","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/2107.08966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Intrinsic rewards can improve exploration in reinforcement learning, but the exploration process may suffer from instability caused by non-stationary reward shaping and strong dependency on hyperparameters. In this work, we introduce Decoupled RL (DeRL) as a general framework which trains separate policies for intrinsically-motivated exploration and exploitation. Such decoupling allows DeRL to leverage the benefits of intrinsic rewards for exploration while demonstrating improved robustness and sample efficiency. We evaluate DeRL algorithms in two sparse-reward environments with multiple types","authors_text":"Filippos Christianos, Josiah P. Hanna, Lukas Sch\\\"afer, Stefano V. Albrecht","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:31:02Z","title":"Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.08966","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":"sha256:43d34ed2f0f6f6dd245e093c660fedbcecb42ea2637531c023e01b78948a7af0","target":"record","created_at":"2026-07-05T03:55:28Z","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":"ee6a9e69b8b7a079f6e72e8c11b82e38e69d1fbad2777bb6323b49b1d1bacd67","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-19T15:31:02Z","title_canon_sha256":"31186a9d8c5fd8f4cfefe600e52eb502533f8d9160d7a8e3fd135c9d2bef7989"},"schema_version":"1.0","source":{"id":"2107.08966","kind":"arxiv","version":3}},"canonical_sha256":"9cd2ea2cadf6bccdd440c5d098debab4df3fba200035b89b527b85895a791f6d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cd2ea2cadf6bccdd440c5d098debab4df3fba200035b89b527b85895a791f6d","first_computed_at":"2026-07-05T03:55:28.623455Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:28.623455Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AooxiXiLO64M65NcU4cF3Pix6UIykW6poXaI51hjf1fmgzD1hjhGldBv1g6CL9P2h/J08wt9XlkSrNJTzcPvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:28.623986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.08966","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43d34ed2f0f6f6dd245e093c660fedbcecb42ea2637531c023e01b78948a7af0","sha256:935a468b70802e924f8f6c748fc9c6ea95d02f29d9ff05a1617efebd290332e0"],"state_sha256":"ee4f432f7d32aa07f47ecaafd23f7085c4253ff06caa83ccb50c2b5fbdde181b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kP8JIwtfF9p3ANO89kufsMxQh1qdUzRnuuH41pIWkHC9nHfxRGrGoj6xakcWmhBadrTK2UQHCpssciRedpKHBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:21:53.612682Z","bundle_sha256":"cff72a2889ef2febf9b5099987419755bbc820092c3c68b9582c1a87d81f92df"}}