{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:Z3W3C7TXGAWC3QAUGP4UA5WQ6G","short_pith_number":"pith:Z3W3C7TX","canonical_record":{"source":{"id":"1910.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-09T17:37:52Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"c8f0187ec56a42c10fcf602ac5ad893500a3d80d217290e7ba3dac478dce8006","abstract_canon_sha256":"1613e31862c9a4d83ae6ce86051e531fd540a2d77c9fb92ffacd1faf67f3269c"},"schema_version":"1.0"},"canonical_sha256":"ceedb17e77302c2dc01433f94076d0f192b582b6853a522eef60eaf35c277da6","source":{"kind":"arxiv","id":"1910.04142","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04142","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04142v1","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04142","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z3W3C7TXGAWC","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z3W3C7TXGAWC3QAU","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z3W3C7TX","created_at":"2026-07-05T00:11:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:Z3W3C7TXGAWC3QAUGP4UA5WQ6G","target":"record","payload":{"canonical_record":{"source":{"id":"1910.04142","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-09T17:37:52Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"c8f0187ec56a42c10fcf602ac5ad893500a3d80d217290e7ba3dac478dce8006","abstract_canon_sha256":"1613e31862c9a4d83ae6ce86051e531fd540a2d77c9fb92ffacd1faf67f3269c"},"schema_version":"1.0"},"canonical_sha256":"ceedb17e77302c2dc01433f94076d0f192b582b6853a522eef60eaf35c277da6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:01.807532Z","signature_b64":"/WGbqGWVfonSiVTmje5/NCBhB2DdIW87ri1vB85N0h2G5wyO8O51xi8dD/id3Lv9lYlSxOjnt5dtpBHIsdVcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ceedb17e77302c2dc01433f94076d0f192b582b6853a522eef60eaf35c277da6","last_reissued_at":"2026-07-05T00:11:01.807064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:01.807064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.04142","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":"2026-07-05T00:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJmxiR27mqkWuzpmToDSxRSWXVq23dp2EV8wXG2vstuCjl9QIeJ8CeJg1Cd/tTTHORuk+DyrnvUtUZXdUlzDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:44:38.687960Z"},"content_sha256":"9889c1889ddafa92ef819e1753353096ad049b3d4f785ba5d775423eb84e5bc5","schema_version":"1.0","event_id":"sha256:9889c1889ddafa92ef819e1753353096ad049b3d4f785ba5d775423eb84e5bc5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:Z3W3C7TXGAWC3QAUGP4UA5WQ6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.RO","authors_text":"Abbas Abdolmaleki, Arunkumar Byravan, Jost Tobias Springenberg, Martin Riedmiller, Michael Neunert, Nicolas Heess, Noah Siegel, Roland Hafner, Thomas Lampe","submitted_at":"2019-10-09T17:37:52Z","abstract_excerpt":"Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper, we explore how model-based Reinforcement Learning (RL) can facilitate transfer to new tasks. We develop an algorithm that learns an action-conditional, predictive model of expected future observations, rewards and values from which a policy can be derived by following the gradient of the estimated value along imagined trajectories. We show how robust policy "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04142","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.04142/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":"2026-07-05T00:11:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PA3TSNj6yISp3Q1nljuE2Y8/vG5zbxcsVKBHF/4X4qHjs8Rl2yCujUqg89IkVPFfdNdYWzke9GSWylo77UHlCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T20:44:38.688712Z"},"content_sha256":"377f6dee5f7cc93e346378732be29ef403a5b306dea1abd5c77b0c8d53b80073","schema_version":"1.0","event_id":"sha256:377f6dee5f7cc93e346378732be29ef403a5b306dea1abd5c77b0c8d53b80073"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/bundle.json","state_url":"https://pith.science/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/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":"2026-08-18T20:44:38Z","links":{"resolver":"https://pith.science/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G","bundle":"https://pith.science/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/bundle.json","state":"https://pith.science/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z3W3C7TXGAWC3QAUGP4UA5WQ6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:Z3W3C7TXGAWC3QAUGP4UA5WQ6G","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":"1613e31862c9a4d83ae6ce86051e531fd540a2d77c9fb92ffacd1faf67f3269c","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-09T17:37:52Z","title_canon_sha256":"c8f0187ec56a42c10fcf602ac5ad893500a3d80d217290e7ba3dac478dce8006"},"schema_version":"1.0","source":{"id":"1910.04142","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.04142","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"arxiv_version","alias_value":"1910.04142v1","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.04142","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z3W3C7TXGAWC","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z3W3C7TXGAWC3QAU","created_at":"2026-07-05T00:11:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z3W3C7TX","created_at":"2026-07-05T00:11:01Z"}],"graph_snapshots":[{"event_id":"sha256:377f6dee5f7cc93e346378732be29ef403a5b306dea1abd5c77b0c8d53b80073","target":"graph","created_at":"2026-07-05T00:11:01Z","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/1910.04142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper, we explore how model-based Reinforcement Learning (RL) can facilitate transfer to new tasks. We develop an algorithm that learns an action-conditional, predictive model of expected future observations, rewards and values from which a policy can be derived by following the gradient of the estimated value along imagined trajectories. We show how robust policy ","authors_text":"Abbas Abdolmaleki, Arunkumar Byravan, Jost Tobias Springenberg, Martin Riedmiller, Michael Neunert, Nicolas Heess, Noah Siegel, Roland Hafner, Thomas Lampe","cross_cats":["cs.AI","cs.CV","cs.LG","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-09T17:37:52Z","title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.04142","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":"sha256:9889c1889ddafa92ef819e1753353096ad049b3d4f785ba5d775423eb84e5bc5","target":"record","created_at":"2026-07-05T00:11:01Z","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":"1613e31862c9a4d83ae6ce86051e531fd540a2d77c9fb92ffacd1faf67f3269c","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-10-09T17:37:52Z","title_canon_sha256":"c8f0187ec56a42c10fcf602ac5ad893500a3d80d217290e7ba3dac478dce8006"},"schema_version":"1.0","source":{"id":"1910.04142","kind":"arxiv","version":1}},"canonical_sha256":"ceedb17e77302c2dc01433f94076d0f192b582b6853a522eef60eaf35c277da6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ceedb17e77302c2dc01433f94076d0f192b582b6853a522eef60eaf35c277da6","first_computed_at":"2026-07-05T00:11:01.807064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:01.807064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/WGbqGWVfonSiVTmje5/NCBhB2DdIW87ri1vB85N0h2G5wyO8O51xi8dD/id3Lv9lYlSxOjnt5dtpBHIsdVcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:01.807532Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.04142","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9889c1889ddafa92ef819e1753353096ad049b3d4f785ba5d775423eb84e5bc5","sha256:377f6dee5f7cc93e346378732be29ef403a5b306dea1abd5c77b0c8d53b80073"],"state_sha256":"fdd0e7ff9c12b83e8a9173e3797c96e20f12ca05d4aeb5e4a22dc621fb0cd20a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HgI+/Q+uF7afxyMWfUVERyJGKU3TBhhw7ReehLGw7SL1njsmPQcyExBNCHmlZdgmatHj7SfZjn+lOAkmngCnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T20:44:38.694323Z","bundle_sha256":"33cb304ea67a21f2d4183fc4978e92d124929eba932d302c1a5ea863cb49088d"}}