{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SDDDVNWV3VGF644JZZ4DSIWZHF","short_pith_number":"pith:SDDDVNWV","canonical_record":{"source":{"id":"1908.06976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T16:22:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7fbba68c50da2dfc3a97a3b83af7ee5b17ef11e88249e45b6b9f65864ac716f2","abstract_canon_sha256":"31fdb2bcc81ff8356c0cdbd34da683648542f3ae6ba5e29166fa05da85f31fc9"},"schema_version":"1.0"},"canonical_sha256":"90c63ab6d5dd4c5f7389ce783922d9397a874462c2bf7dd9a2cb36a41904e867","source":{"kind":"arxiv","id":"1908.06976","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06976","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06976v2","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06976","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"SDDDVNWV3VGF","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_16","alias_value":"SDDDVNWV3VGF644J","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_8","alias_value":"SDDDVNWV","created_at":"2026-07-05T00:20:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SDDDVNWV3VGF644JZZ4DSIWZHF","target":"record","payload":{"canonical_record":{"source":{"id":"1908.06976","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T16:22:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7fbba68c50da2dfc3a97a3b83af7ee5b17ef11e88249e45b6b9f65864ac716f2","abstract_canon_sha256":"31fdb2bcc81ff8356c0cdbd34da683648542f3ae6ba5e29166fa05da85f31fc9"},"schema_version":"1.0"},"canonical_sha256":"90c63ab6d5dd4c5f7389ce783922d9397a874462c2bf7dd9a2cb36a41904e867","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:18.746511Z","signature_b64":"5vFcRGkPWukUxo4NxSlhMicrTOAPk30X8P9OHb6+f9lgh7NZ/fEcR2BNXfrUjdni00xs8qK7DxdVAfRMGlq8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90c63ab6d5dd4c5f7389ce783922d9397a874462c2bf7dd9a2cb36a41904e867","last_reissued_at":"2026-07-05T00:20:18.746089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:18.746089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.06976","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:20:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4rNMje8auioXxY1fXozXwyxz+da0NBswtDkkvQc5VETnFT9SWhqYo5YfdfvWM6Qi9cOYBaizKZ26CrplNT5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:30:26.170383Z"},"content_sha256":"df4afc4f3013d37cafacfec0034343aaa22b1fee2859e50523397a29111274ab","schema_version":"1.0","event_id":"sha256:df4afc4f3013d37cafacfec0034343aaa22b1fee2859e50523397a29111274ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SDDDVNWV3VGF644JZZ4DSIWZHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A survey on intrinsic motivation in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Arthur Aubret, Laetitia Matignon, Salima Hassas","submitted_at":"2019-08-19T16:22:20Z","abstract_excerpt":"The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL). However a number of scientific and technical challenges still need to be addressed, amongst which we can mention the ability to abstract actions or the difficulty to explore the environment which can be addressed by intrinsic motivation (IM). In this article, we provide a survey on the role of intrinsic motivation in DRL. We categorize the different kinds of intrinsic motivations and detail for each category, its advantages and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06976","kind":"arxiv","version":2},"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/1908.06976/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":"2026-07-05T00:20:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmghicqZb12Xh1DLqpKNOjyBgO1JXr9tscIq3qXSjppivCc9iUwB8oLjNdfOtYvVrEUxuOSOb5je80VzkFojBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T23:30:26.171001Z"},"content_sha256":"889fb4e635e72cd192cddcdbe1d9469b73f2ae0f4cc432484fa469678932b472","schema_version":"1.0","event_id":"sha256:889fb4e635e72cd192cddcdbe1d9469b73f2ae0f4cc432484fa469678932b472"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/bundle.json","state_url":"https://pith.science/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/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":"2026-08-16T23:30:26Z","links":{"resolver":"https://pith.science/pith/SDDDVNWV3VGF644JZZ4DSIWZHF","bundle":"https://pith.science/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/bundle.json","state":"https://pith.science/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDDDVNWV3VGF644JZZ4DSIWZHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SDDDVNWV3VGF644JZZ4DSIWZHF","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":"31fdb2bcc81ff8356c0cdbd34da683648542f3ae6ba5e29166fa05da85f31fc9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T16:22:20Z","title_canon_sha256":"7fbba68c50da2dfc3a97a3b83af7ee5b17ef11e88249e45b6b9f65864ac716f2"},"schema_version":"1.0","source":{"id":"1908.06976","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.06976","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"arxiv_version","alias_value":"1908.06976v2","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.06976","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_12","alias_value":"SDDDVNWV3VGF","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_16","alias_value":"SDDDVNWV3VGF644J","created_at":"2026-07-05T00:20:18Z"},{"alias_kind":"pith_short_8","alias_value":"SDDDVNWV","created_at":"2026-07-05T00:20:18Z"}],"graph_snapshots":[{"event_id":"sha256:889fb4e635e72cd192cddcdbe1d9469b73f2ae0f4cc432484fa469678932b472","target":"graph","created_at":"2026-07-05T00:20:18Z","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/1908.06976/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The reinforcement learning (RL) research area is very active, with an important number of new contributions; especially considering the emergent field of deep RL (DRL). However a number of scientific and technical challenges still need to be addressed, amongst which we can mention the ability to abstract actions or the difficulty to explore the environment which can be addressed by intrinsic motivation (IM). In this article, we provide a survey on the role of intrinsic motivation in DRL. We categorize the different kinds of intrinsic motivations and detail for each category, its advantages and","authors_text":"Arthur Aubret, Laetitia Matignon, Salima Hassas","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T16:22:20Z","title":"A survey on intrinsic motivation in reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.06976","kind":"arxiv","version":2},"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:df4afc4f3013d37cafacfec0034343aaa22b1fee2859e50523397a29111274ab","target":"record","created_at":"2026-07-05T00:20:18Z","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":"31fdb2bcc81ff8356c0cdbd34da683648542f3ae6ba5e29166fa05da85f31fc9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-19T16:22:20Z","title_canon_sha256":"7fbba68c50da2dfc3a97a3b83af7ee5b17ef11e88249e45b6b9f65864ac716f2"},"schema_version":"1.0","source":{"id":"1908.06976","kind":"arxiv","version":2}},"canonical_sha256":"90c63ab6d5dd4c5f7389ce783922d9397a874462c2bf7dd9a2cb36a41904e867","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90c63ab6d5dd4c5f7389ce783922d9397a874462c2bf7dd9a2cb36a41904e867","first_computed_at":"2026-07-05T00:20:18.746089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:18.746089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5vFcRGkPWukUxo4NxSlhMicrTOAPk30X8P9OHb6+f9lgh7NZ/fEcR2BNXfrUjdni00xs8qK7DxdVAfRMGlq8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:18.746511Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.06976","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df4afc4f3013d37cafacfec0034343aaa22b1fee2859e50523397a29111274ab","sha256:889fb4e635e72cd192cddcdbe1d9469b73f2ae0f4cc432484fa469678932b472"],"state_sha256":"700117684c3f7a6849d53b87ed2b749ab68127bdc1bfc34897b5aa836b91aab3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlxIbtbbrlsqU7v1A9cdr8htcrOeg/xGFDeHcETKXF8EXBcoqdeKL1FXNgZ3o3N3s6qwis6Wp+LQAvBRB6zQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T23:30:26.176845Z","bundle_sha256":"18eaaf169f6c6bc572dc4b28f656d3ee2c0dc6840ae804db1871446dc4618954"}}