{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:K4U6FZBQZU3HTU6WA46LVXEDYP","short_pith_number":"pith:K4U6FZBQ","canonical_record":{"source":{"id":"1707.08475","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-26T14:50:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"474dfef33e5045b7c0552a77ca242dac8ed7ac5071ad9fde242426d69beaffdb","abstract_canon_sha256":"9f91acd01e2565dd290ef3653cea9a9ad3632872b70dda376a035496bb44d076"},"schema_version":"1.0"},"canonical_sha256":"5729e2e430cd3679d3d6073cbadc83c3feb0a4503e5c3324c7578a4dcfc74cd7","source":{"kind":"arxiv","id":"1707.08475","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.08475","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1707.08475v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08475","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"K4U6FZBQZU3H","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K4U6FZBQZU3HTU6W","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K4U6FZBQ","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:K4U6FZBQZU3HTU6WA46LVXEDYP","target":"record","payload":{"canonical_record":{"source":{"id":"1707.08475","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-26T14:50:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"474dfef33e5045b7c0552a77ca242dac8ed7ac5071ad9fde242426d69beaffdb","abstract_canon_sha256":"9f91acd01e2565dd290ef3653cea9a9ad3632872b70dda376a035496bb44d076"},"schema_version":"1.0"},"canonical_sha256":"5729e2e430cd3679d3d6073cbadc83c3feb0a4503e5c3324c7578a4dcfc74cd7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.746681Z","signature_b64":"pF+D3gCxUKcR6460OB6TKbgF7AMcCb305metBnFGtCmCTteJBsiYdc+oHb0sGXvkE692uOeowXMnAtumZY+/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5729e2e430cd3679d3d6073cbadc83c3feb0a4503e5c3324c7578a4dcfc74cd7","last_reissued_at":"2026-05-18T00:14:06.746217Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.746217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.08475","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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYDUG5ZRxA5wTBA1+Yo5oAVEKAvWCIqOLknGieLSDMYWOUCfoAzxx0+Q2SBruhf7On6jcumrzGgEl42rDl2ZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:56:07.769086Z"},"content_sha256":"297eec3074af21d40962428bca1792abfebf5c7802b130d73669ee5ff69f6f0c","schema_version":"1.0","event_id":"sha256:297eec3074af21d40962428bca1792abfebf5c7802b130d73669ee5ff69f6f0c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:K4U6FZBQZU3HTU6WA46LVXEDYP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Lerchner, Alexander Pritzel, Andrei A. Rusu, Arka Pal, Charles Blundell, Christopher P Burgess, Irina Higgins, Loic Matthey, Matthew Botvinick","submitted_at":"2017-07-26T14:50:51Z","abstract_excerpt":"Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08475","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":"2026-05-18T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9dWB5o8Tx8gVrwW8UWC35fTY2QvC6/2v9wv+qw8VRf4Er58c/JKxKxU7r7dYEiCkLJKy51B/Cbwvh8mFQI5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:56:07.769799Z"},"content_sha256":"42dbde064e5640cef82c115eb9928d6fa65c11146a59f1b98085e043e9ff0341","schema_version":"1.0","event_id":"sha256:42dbde064e5640cef82c115eb9928d6fa65c11146a59f1b98085e043e9ff0341"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/bundle.json","state_url":"https://pith.science/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/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":"2026-05-25T18:56:07Z","links":{"resolver":"https://pith.science/pith/K4U6FZBQZU3HTU6WA46LVXEDYP","bundle":"https://pith.science/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/bundle.json","state":"https://pith.science/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4U6FZBQZU3HTU6WA46LVXEDYP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:K4U6FZBQZU3HTU6WA46LVXEDYP","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":"9f91acd01e2565dd290ef3653cea9a9ad3632872b70dda376a035496bb44d076","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-26T14:50:51Z","title_canon_sha256":"474dfef33e5045b7c0552a77ca242dac8ed7ac5071ad9fde242426d69beaffdb"},"schema_version":"1.0","source":{"id":"1707.08475","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.08475","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"1707.08475v2","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08475","created_at":"2026-05-18T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"K4U6FZBQZU3H","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"K4U6FZBQZU3HTU6W","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"K4U6FZBQ","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:42dbde064e5640cef82c115eb9928d6fa65c11146a59f1b98085e043e9ff0341","target":"graph","created_at":"2026-05-18T00:14:06Z","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":"Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, with the hope that it generalises well to the target domain. We propose a new multi-stage RL agent, DARLA (DisentAngled Representation Learning Agent), which learns to see before learning to act. DARLA's vision is based on learning a disentangled representation of the observed environment. Once DARLA can see, it is able to acquire source policies that are robust to many domain ","authors_text":"Alexander Lerchner, Alexander Pritzel, Andrei A. Rusu, Arka Pal, Charles Blundell, Christopher P Burgess, Irina Higgins, Loic Matthey, Matthew Botvinick","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-26T14:50:51Z","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08475","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":"sha256:297eec3074af21d40962428bca1792abfebf5c7802b130d73669ee5ff69f6f0c","target":"record","created_at":"2026-05-18T00:14:06Z","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":"9f91acd01e2565dd290ef3653cea9a9ad3632872b70dda376a035496bb44d076","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-07-26T14:50:51Z","title_canon_sha256":"474dfef33e5045b7c0552a77ca242dac8ed7ac5071ad9fde242426d69beaffdb"},"schema_version":"1.0","source":{"id":"1707.08475","kind":"arxiv","version":2}},"canonical_sha256":"5729e2e430cd3679d3d6073cbadc83c3feb0a4503e5c3324c7578a4dcfc74cd7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5729e2e430cd3679d3d6073cbadc83c3feb0a4503e5c3324c7578a4dcfc74cd7","first_computed_at":"2026-05-18T00:14:06.746217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:06.746217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pF+D3gCxUKcR6460OB6TKbgF7AMcCb305metBnFGtCmCTteJBsiYdc+oHb0sGXvkE692uOeowXMnAtumZY+/AQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:06.746681Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.08475","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:297eec3074af21d40962428bca1792abfebf5c7802b130d73669ee5ff69f6f0c","sha256:42dbde064e5640cef82c115eb9928d6fa65c11146a59f1b98085e043e9ff0341"],"state_sha256":"a61276359fc45a411cf6b81f70cbc529ce6cec2add3df74dd764764d73f28b65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AtjCWG8qDK+pdtkLQtQa3ZibSsn/+J0qZVUpp6Fu/Lggyfjvb/D/5FxeffWZwGV3ky6guutmYyuvYlQ/BQWcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:56:07.777273Z","bundle_sha256":"3e4649143d08309d6d7f798bfea02cb739cdaf0b42a67da8ff8fdb3803a213b4"}}