{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QQVZ4Z5TFV2HLMIH6WOVT2J3AS","short_pith_number":"pith:QQVZ4Z5T","canonical_record":{"source":{"id":"1804.01238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"798467550a8686512be65141c6606adb29c2fbf547e55a6b68eecf3bff6eeaf3","abstract_canon_sha256":"7ae2c60aa90b88bcebc687ef2675034e1f5805e41b12d394741132d1a1c917a7"},"schema_version":"1.0"},"canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","source":{"kind":"arxiv","id":"1804.01238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01238","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01238v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01238","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"QQVZ4Z5TFV2H","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QQVZ4Z5TFV2HLMIH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QQVZ4Z5T","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QQVZ4Z5TFV2HLMIH6WOVT2J3AS","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"798467550a8686512be65141c6606adb29c2fbf547e55a6b68eecf3bff6eeaf3","abstract_canon_sha256":"7ae2c60aa90b88bcebc687ef2675034e1f5805e41b12d394741132d1a1c917a7"},"schema_version":"1.0"},"canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:15.640203Z","signature_b64":"8Q/L1i4+Z1rukXTzeyZAbiUJOZADyHNLS85QhiU+mfqG2sJs5MfE7VunPia60EV3jWRLgK7WCsAttEG1Cya5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","last_reissued_at":"2026-05-18T00:19:15.639518Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:15.639518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01238","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pCmbQorSfTkWW1okgIYwmyw+5O3JDZx+EuQWX3Y58oxCDMZNldo2GIgTvELclkuPWVZmkDxre120xBRxP/oOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:10:49.110810Z"},"content_sha256":"3720fc546a86ba98d511086be9826b5af6590d12629ebcc614d07831bb6bf621","schema_version":"1.0","event_id":"sha256:3720fc546a86ba98d511086be9826b5af6590d12629ebcc614d07831bb6bf621"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QQVZ4Z5TFV2HLMIH6WOVT2J3AS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Information Maximizing Exploration with a Latent Dynamics Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Heni Ben Amor, Oliver Obst, Trevor Barron","submitted_at":"2018-04-04T05:04:41Z","abstract_excerpt":"All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient methods or $\\epsilon$-greedy in Q-learning. While these methods are appealing due to their simplicity, they do not explore the state space in a methodical manner. We present an approach that uses a model to derive reward bonuses as a means of intrinsic motivation to improve model-free reinforcement learning. A key insight of our approach is that this dynamics m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01238","kind":"arxiv","version":1},"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":"2026-05-18T00:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V4PaZm0CF5JJe+ededZarDcDUVFC7oe6atk8zMmzcY3N3Dnltol67+DSxwshEqCJDszS0F15SH4oTfoqn7DIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:10:49.111155Z"},"content_sha256":"1bb95ff796faf6c58f47f1985f72bfee1513025d95f3d11b56a026ff66a9c924","schema_version":"1.0","event_id":"sha256:1bb95ff796faf6c58f47f1985f72bfee1513025d95f3d11b56a026ff66a9c924"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/bundle.json","state_url":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/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":"2026-06-27T08:10:49Z","links":{"resolver":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS","bundle":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/bundle.json","state":"https://pith.science/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQVZ4Z5TFV2HLMIH6WOVT2J3AS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QQVZ4Z5TFV2HLMIH6WOVT2J3AS","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":"7ae2c60aa90b88bcebc687ef2675034e1f5805e41b12d394741132d1a1c917a7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","title_canon_sha256":"798467550a8686512be65141c6606adb29c2fbf547e55a6b68eecf3bff6eeaf3"},"schema_version":"1.0","source":{"id":"1804.01238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01238","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01238v1","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01238","created_at":"2026-05-18T00:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"QQVZ4Z5TFV2H","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QQVZ4Z5TFV2HLMIH","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QQVZ4Z5T","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:1bb95ff796faf6c58f47f1985f72bfee1513025d95f3d11b56a026ff66a9c924","target":"graph","created_at":"2026-05-18T00:19:15Z","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":"All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient methods or $\\epsilon$-greedy in Q-learning. While these methods are appealing due to their simplicity, they do not explore the state space in a methodical manner. We present an approach that uses a model to derive reward bonuses as a means of intrinsic motivation to improve model-free reinforcement learning. A key insight of our approach is that this dynamics m","authors_text":"Heni Ben Amor, Oliver Obst, Trevor Barron","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","title":"Information Maximizing Exploration with a Latent Dynamics Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01238","kind":"arxiv","version":1},"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":"sha256:3720fc546a86ba98d511086be9826b5af6590d12629ebcc614d07831bb6bf621","target":"record","created_at":"2026-05-18T00:19:15Z","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":"7ae2c60aa90b88bcebc687ef2675034e1f5805e41b12d394741132d1a1c917a7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-04T05:04:41Z","title_canon_sha256":"798467550a8686512be65141c6606adb29c2fbf547e55a6b68eecf3bff6eeaf3"},"schema_version":"1.0","source":{"id":"1804.01238","kind":"arxiv","version":1}},"canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"842b9e67b32d7475b107f59d59e93b048b9a04b138f3294b88d6ab3acf8bf6d3","first_computed_at":"2026-05-18T00:19:15.639518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:15.639518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8Q/L1i4+Z1rukXTzeyZAbiUJOZADyHNLS85QhiU+mfqG2sJs5MfE7VunPia60EV3jWRLgK7WCsAttEG1Cya5Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:15.640203Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3720fc546a86ba98d511086be9826b5af6590d12629ebcc614d07831bb6bf621","sha256:1bb95ff796faf6c58f47f1985f72bfee1513025d95f3d11b56a026ff66a9c924"],"state_sha256":"c5e401e3e9f03a3af42f75a8209e657601120797b60d7671d6cb8c503d7e56b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPFvUcj7oZKndvpXo51t1FRk3WZjxkYVWhZ3MhmpAFo41NbEkU9noax5ito4lAzV1dy4Ow0xa97wrNefFBI7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T08:10:49.113075Z","bundle_sha256":"adebf86ca24047ce095e94e90408833b77cbe59fc8f32ad65f4ea7a6235268ae"}}