{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:UBDSHIZR6VOXHGUSNZR3I274LL","short_pith_number":"pith:UBDSHIZR","canonical_record":{"source":{"id":"1802.05054","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T11:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"745f4052143b67af2f5caaf64e192f47143a39aff801754af507c5891ec0c781","abstract_canon_sha256":"952a2719fb89a06a2ea897821e6622d97b55d5c0f3fa84159c9524e221892046"},"schema_version":"1.0"},"canonical_sha256":"a04723a331f55d739a926e63b46bfc5aea23a560ed882d4f5a6b6a7e77149616","source":{"kind":"arxiv","id":"1802.05054","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05054","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05054v5","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05054","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"UBDSHIZR6VOX","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UBDSHIZR6VOXHGUS","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UBDSHIZR","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:UBDSHIZR6VOXHGUSNZR3I274LL","target":"record","payload":{"canonical_record":{"source":{"id":"1802.05054","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T11:59:21Z","cross_cats_sorted":[],"title_canon_sha256":"745f4052143b67af2f5caaf64e192f47143a39aff801754af507c5891ec0c781","abstract_canon_sha256":"952a2719fb89a06a2ea897821e6622d97b55d5c0f3fa84159c9524e221892046"},"schema_version":"1.0"},"canonical_sha256":"a04723a331f55d739a926e63b46bfc5aea23a560ed882d4f5a6b6a7e77149616","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:19.475742Z","signature_b64":"k1nVu8LnU0nDdU5tKpxVCM57OCxTDEL/f7NIKJ4Wl3DM28iCN0Uf2qpgceFHSEltDnleqvJV2gIBSt96yduvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a04723a331f55d739a926e63b46bfc5aea23a560ed882d4f5a6b6a7e77149616","last_reissued_at":"2026-05-18T00:05:19.475264Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:19.475264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.05054","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QLSvedPw/O6u9IVmyc6Gj8bh/d9999LRAiEvwSkvIDH9NRO+TNK8/09nTi+n3u1MjTjUvCCFq2ZWp6wgUtrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:23:21.470808Z"},"content_sha256":"b33bd875af8a09cc170178f974172c09f4dfa14ac0929b017c081d8303b8b075","schema_version":"1.0","event_id":"sha256:b33bd875af8a09cc170178f974172c09f4dfa14ac0929b017c081d8303b8b075"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:UBDSHIZR6VOXHGUSNZR3I274LL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","submitted_at":"2018-02-14T11:59:21Z","abstract_excerpt":"In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Conversely, evolutionary and developmental methods focusing on exploration like Novelty Search, Quality-Diversity or Goal Exploration Processes explore more robustly but are less efficient at fine-tuning policies using gradient descent. In this paper, we present the GEP-PG approach, taking the best of both worlds by sequentially combining a Goal Exploration Process and two variants of DDPG. We study the learning performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05054","kind":"arxiv","version":5},"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":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FljkMdeAG4VqUDMCosT5F6ObExlpQT9poaHl+e37cJXbjgBrh2829gYsSMjryuS2D4LMG/gV2ZyWqlWwuZ3LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T11:23:21.471138Z"},"content_sha256":"a86c790bf0163df5586c48a102f1413254d4235750202f2da9fa18d78b647c6f","schema_version":"1.0","event_id":"sha256:a86c790bf0163df5586c48a102f1413254d4235750202f2da9fa18d78b647c6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBDSHIZR6VOXHGUSNZR3I274LL/bundle.json","state_url":"https://pith.science/pith/UBDSHIZR6VOXHGUSNZR3I274LL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBDSHIZR6VOXHGUSNZR3I274LL/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":"2026-06-02T11:23:21Z","links":{"resolver":"https://pith.science/pith/UBDSHIZR6VOXHGUSNZR3I274LL","bundle":"https://pith.science/pith/UBDSHIZR6VOXHGUSNZR3I274LL/bundle.json","state":"https://pith.science/pith/UBDSHIZR6VOXHGUSNZR3I274LL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBDSHIZR6VOXHGUSNZR3I274LL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:UBDSHIZR6VOXHGUSNZR3I274LL","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":"952a2719fb89a06a2ea897821e6622d97b55d5c0f3fa84159c9524e221892046","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T11:59:21Z","title_canon_sha256":"745f4052143b67af2f5caaf64e192f47143a39aff801754af507c5891ec0c781"},"schema_version":"1.0","source":{"id":"1802.05054","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.05054","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1802.05054v5","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.05054","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"UBDSHIZR6VOX","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"UBDSHIZR6VOXHGUS","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"UBDSHIZR","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:a86c790bf0163df5586c48a102f1413254d4235750202f2da9fa18d78b647c6f","target":"graph","created_at":"2026-05-18T00:05:19Z","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":"In continuous action domains, standard deep reinforcement learning algorithms like DDPG suffer from inefficient exploration when facing sparse or deceptive reward problems. Conversely, evolutionary and developmental methods focusing on exploration like Novelty Search, Quality-Diversity or Goal Exploration Processes explore more robustly but are less efficient at fine-tuning policies using gradient descent. In this paper, we present the GEP-PG approach, taking the best of both worlds by sequentially combining a Goal Exploration Process and two variants of DDPG. We study the learning performance","authors_text":"C\\'edric Colas, Olivier Sigaud, Pierre-Yves Oudeyer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T11:59:21Z","title":"GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.05054","kind":"arxiv","version":5},"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:b33bd875af8a09cc170178f974172c09f4dfa14ac0929b017c081d8303b8b075","target":"record","created_at":"2026-05-18T00:05:19Z","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":"952a2719fb89a06a2ea897821e6622d97b55d5c0f3fa84159c9524e221892046","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-14T11:59:21Z","title_canon_sha256":"745f4052143b67af2f5caaf64e192f47143a39aff801754af507c5891ec0c781"},"schema_version":"1.0","source":{"id":"1802.05054","kind":"arxiv","version":5}},"canonical_sha256":"a04723a331f55d739a926e63b46bfc5aea23a560ed882d4f5a6b6a7e77149616","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a04723a331f55d739a926e63b46bfc5aea23a560ed882d4f5a6b6a7e77149616","first_computed_at":"2026-05-18T00:05:19.475264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:19.475264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k1nVu8LnU0nDdU5tKpxVCM57OCxTDEL/f7NIKJ4Wl3DM28iCN0Uf2qpgceFHSEltDnleqvJV2gIBSt96yduvAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:19.475742Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.05054","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b33bd875af8a09cc170178f974172c09f4dfa14ac0929b017c081d8303b8b075","sha256:a86c790bf0163df5586c48a102f1413254d4235750202f2da9fa18d78b647c6f"],"state_sha256":"05f1612cbe0d49040e61688a688c1596b7c1a963e73507405a516bdfdc2901e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ulq08o+05BbX4q/gcHbwTn009/jv+h6GR1H457s9NC7DqDAogj2xl002krYTaNV7c87iZGlzNHpd4TsLZUzBCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T11:23:21.473050Z","bundle_sha256":"9ab7f07ae27c15c38cfd251951ee443fcad410ffbee14202102de633e532bf69"}}