{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XILQUYTSVCFXOJ3SCCSIXCPX2I","short_pith_number":"pith:XILQUYTS","canonical_record":{"source":{"id":"1810.11388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T15:32:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bddf0ec8f443fda9c4ade0f994517d08ce660d0569a0157d5e8e6752b1ed6434","abstract_canon_sha256":"160beee0e4adf91cf2b72f0708d034672b8a54d91ad9c668224ac64eaf814f60"},"schema_version":"1.0"},"canonical_sha256":"ba170a6272a88b77277210a48b89f7d216f11489535b2c256e33ae46f9846260","source":{"kind":"arxiv","id":"1810.11388","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11388","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11388v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11388","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"XILQUYTSVCFX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XILQUYTSVCFXOJ3S","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XILQUYTS","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XILQUYTSVCFXOJ3SCCSIXCPX2I","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T15:32:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"bddf0ec8f443fda9c4ade0f994517d08ce660d0569a0157d5e8e6752b1ed6434","abstract_canon_sha256":"160beee0e4adf91cf2b72f0708d034672b8a54d91ad9c668224ac64eaf814f60"},"schema_version":"1.0"},"canonical_sha256":"ba170a6272a88b77277210a48b89f7d216f11489535b2c256e33ae46f9846260","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.448632Z","signature_b64":"TEiUylcoOGkmSXgoZLVuoF8+tzSyXFPeHmcFwgFJ8x2LZkT+31FN/biWEl6vQQVdwofE/XdqSQo1X1lrKR/GDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba170a6272a88b77277210a48b89f7d216f11489535b2c256e33ae46f9846260","last_reissued_at":"2026-05-17T23:53:50.447843Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.447843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11388","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":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bP6RUZLbCIl4eLG1S5II1XZ1YvkqQtNYplIEoFLp2Xb99q3GGHQUCPYVX0HfkUdFhlUHoMWbQe5Lzqd5hxtRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:30:04.767803Z"},"content_sha256":"b5102162eb6f4c21474f959dfcd506e86f21309dcf3537f621cd092874e8ee26","schema_version":"1.0","event_id":"sha256:b5102162eb6f4c21474f959dfcd506e86f21309dcf3537f621cd092874e8ee26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XILQUYTSVCFXOJ3SCCSIXCPX2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Cornelius Weber, Matthias Kerzel, Muhammad Burhan Hafez, Stefan Wermter","submitted_at":"2018-10-26T15:32:32Z","abstract_excerpt":"In this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencoder which is trained to reconstruct the visual input, while the centre-most hidden representation is also optimized to estimate the state value. Separately, an ensemble of predictive world models generates, based on its learning progress, an intrinsic reward signal which is combined with the extrinsic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11388","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":""},"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":"2026-05-17T23:53:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mX1oCY3s07nuR4CEzhYGMwl56tKDNUahDPdx4RpcqeiBsm82EtXj1F7oSf7o2v/HgcZBJINCSx1wkBlLeAHPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T09:30:04.768485Z"},"content_sha256":"d4adc4d2abb7baf27236b4d58a8fdd79f83ceccdf56d0a4f732506f63c4f35b5","schema_version":"1.0","event_id":"sha256:d4adc4d2abb7baf27236b4d58a8fdd79f83ceccdf56d0a4f732506f63c4f35b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/bundle.json","state_url":"https://pith.science/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/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":"2026-05-30T09:30:04Z","links":{"resolver":"https://pith.science/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I","bundle":"https://pith.science/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/bundle.json","state":"https://pith.science/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XILQUYTSVCFXOJ3SCCSIXCPX2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XILQUYTSVCFXOJ3SCCSIXCPX2I","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":"160beee0e4adf91cf2b72f0708d034672b8a54d91ad9c668224ac64eaf814f60","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T15:32:32Z","title_canon_sha256":"bddf0ec8f443fda9c4ade0f994517d08ce660d0569a0157d5e8e6752b1ed6434"},"schema_version":"1.0","source":{"id":"1810.11388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11388","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11388v2","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11388","created_at":"2026-05-17T23:53:50Z"},{"alias_kind":"pith_short_12","alias_value":"XILQUYTSVCFX","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XILQUYTSVCFXOJ3S","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XILQUYTS","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:d4adc4d2abb7baf27236b4d58a8fdd79f83ceccdf56d0a4f732506f63c4f35b5","target":"graph","created_at":"2026-05-17T23:53:50Z","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 this paper, we present a new intrinsically motivated actor-critic algorithm for learning continuous motor skills directly from raw visual input. Our neural architecture is composed of a critic and an actor network. Both networks receive the hidden representation of a deep convolutional autoencoder which is trained to reconstruct the visual input, while the centre-most hidden representation is also optimized to estimate the state value. Separately, an ensemble of predictive world models generates, based on its learning progress, an intrinsic reward signal which is combined with the extrinsic","authors_text":"Cornelius Weber, Matthias Kerzel, Muhammad Burhan Hafez, Stefan Wermter","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T15:32:32Z","title":"Deep Intrinsically Motivated Continuous Actor-Critic for Efficient Robotic Visuomotor Skill Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11388","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:b5102162eb6f4c21474f959dfcd506e86f21309dcf3537f621cd092874e8ee26","target":"record","created_at":"2026-05-17T23:53:50Z","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":"160beee0e4adf91cf2b72f0708d034672b8a54d91ad9c668224ac64eaf814f60","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T15:32:32Z","title_canon_sha256":"bddf0ec8f443fda9c4ade0f994517d08ce660d0569a0157d5e8e6752b1ed6434"},"schema_version":"1.0","source":{"id":"1810.11388","kind":"arxiv","version":2}},"canonical_sha256":"ba170a6272a88b77277210a48b89f7d216f11489535b2c256e33ae46f9846260","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba170a6272a88b77277210a48b89f7d216f11489535b2c256e33ae46f9846260","first_computed_at":"2026-05-17T23:53:50.447843Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:50.447843Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TEiUylcoOGkmSXgoZLVuoF8+tzSyXFPeHmcFwgFJ8x2LZkT+31FN/biWEl6vQQVdwofE/XdqSQo1X1lrKR/GDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:50.448632Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5102162eb6f4c21474f959dfcd506e86f21309dcf3537f621cd092874e8ee26","sha256:d4adc4d2abb7baf27236b4d58a8fdd79f83ceccdf56d0a4f732506f63c4f35b5"],"state_sha256":"523bb4f7889e30ac674b6a298b73f40511d3cc78aebc34c4c2ec742ab9416e39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D9qVLq/+6QHzOT83QHid5ek8N4URlatAdCBHzHWsSs5P0uZB4E7p7xPi2rU245WS+30H3iOTXzVSX9wMOXvLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T09:30:04.771854Z","bundle_sha256":"e6ecedd8a2ae57dfc7065fca7b072911bc1462ff33c8b7b3ae25c56c6a1938f3"}}