{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LC3FRDCR7ZJQTDS4MOATK3RQ2Y","short_pith_number":"pith:LC3FRDCR","canonical_record":{"source":{"id":"1906.04452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:06:19Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"0cbb0d42554195f19dcd7dcb1f9896e476aceb8479d4bc82a895d869bd497f25","abstract_canon_sha256":"2b206fe7da86ca48bd6e4c32ebc29291216a081e03cf295b6a5afa5f9291eb1a"},"schema_version":"1.0"},"canonical_sha256":"58b6588c51fe53098e5c6381356e30d6395fb2b99df5ec754d2867e71bc43e4b","source":{"kind":"arxiv","id":"1906.04452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04452","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04452v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04452","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"LC3FRDCR7ZJQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LC3FRDCR7ZJQTDS4","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LC3FRDCR","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LC3FRDCR7ZJQTDS4MOATK3RQ2Y","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:06:19Z","cross_cats_sorted":["cs.RO","stat.ML"],"title_canon_sha256":"0cbb0d42554195f19dcd7dcb1f9896e476aceb8479d4bc82a895d869bd497f25","abstract_canon_sha256":"2b206fe7da86ca48bd6e4c32ebc29291216a081e03cf295b6a5afa5f9291eb1a"},"schema_version":"1.0"},"canonical_sha256":"58b6588c51fe53098e5c6381356e30d6395fb2b99df5ec754d2867e71bc43e4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:39.227263Z","signature_b64":"Ob0iXRvxssgyqxBNl2nJdiZJufKaLsx2U9ARGkwtJ+MNT08Yeh1pn1CowWcDMJpaq48BOOR8JzScXZCwarmkBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b6588c51fe53098e5c6381356e30d6395fb2b99df5ec754d2867e71bc43e4b","last_reissued_at":"2026-05-17T23:43:39.226537Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:39.226537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04452","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbnGXX04V7/Bkq/Y6c69h7nnKVxcStOH1Jwd7lVUTZNFnFJpVH0fWdS2LNHZMz7/C3m4J3IREYZLIo5Dy7DOCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:38:58.840131Z"},"content_sha256":"b2b08bb336e2721a5903b99176d504c619d320fe48486ba86691237f44f10f78","schema_version":"1.0","event_id":"sha256:b2b08bb336e2721a5903b99176d504c619d320fe48486ba86691237f44f10f78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LC3FRDCR7ZJQTDS4MOATK3RQ2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Natalia D\\'iaz-Rodr\\'iguez, Ren\\'e Traor\\'e, Te Sun, Timoth\\'ee Lesort","submitted_at":"2019-06-11T09:06:19Z","abstract_excerpt":"We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to comb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04452","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":"2026-05-17T23:43:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N0XFKwTxGTGeG/nhGu+kgHdsv/ZOxpPWNKgFogwUsx8diJAL8fh0OwKlhu5gDoexIi4WRMa31CVJvGSaCbjJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:38:58.840828Z"},"content_sha256":"53e985cf8fd48ab6198f9f99f6df94a5886e49722c2ef220fe55d9ca3973cc7a","schema_version":"1.0","event_id":"sha256:53e985cf8fd48ab6198f9f99f6df94a5886e49722c2ef220fe55d9ca3973cc7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/bundle.json","state_url":"https://pith.science/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/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":"2026-05-26T19:38:58Z","links":{"resolver":"https://pith.science/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y","bundle":"https://pith.science/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/bundle.json","state":"https://pith.science/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LC3FRDCR7ZJQTDS4MOATK3RQ2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LC3FRDCR7ZJQTDS4MOATK3RQ2Y","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":"2b206fe7da86ca48bd6e4c32ebc29291216a081e03cf295b6a5afa5f9291eb1a","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:06:19Z","title_canon_sha256":"0cbb0d42554195f19dcd7dcb1f9896e476aceb8479d4bc82a895d869bd497f25"},"schema_version":"1.0","source":{"id":"1906.04452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04452","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04452v1","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04452","created_at":"2026-05-17T23:43:39Z"},{"alias_kind":"pith_short_12","alias_value":"LC3FRDCR7ZJQ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LC3FRDCR7ZJQTDS4","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LC3FRDCR","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:53e985cf8fd48ab6198f9f99f6df94a5886e49722c2ef220fe55d9ca3973cc7a","target":"graph","created_at":"2026-05-17T23:43:39Z","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":"We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to comb","authors_text":"David Filliat, Hugo Caselles-Dupr\\'e, Natalia D\\'iaz-Rodr\\'iguez, Ren\\'e Traor\\'e, Te Sun, Timoth\\'ee Lesort","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:06:19Z","title":"Continual Reinforcement Learning deployed in Real-life using Policy Distillation and Sim2Real Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04452","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:b2b08bb336e2721a5903b99176d504c619d320fe48486ba86691237f44f10f78","target":"record","created_at":"2026-05-17T23:43:39Z","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":"2b206fe7da86ca48bd6e4c32ebc29291216a081e03cf295b6a5afa5f9291eb1a","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-11T09:06:19Z","title_canon_sha256":"0cbb0d42554195f19dcd7dcb1f9896e476aceb8479d4bc82a895d869bd497f25"},"schema_version":"1.0","source":{"id":"1906.04452","kind":"arxiv","version":1}},"canonical_sha256":"58b6588c51fe53098e5c6381356e30d6395fb2b99df5ec754d2867e71bc43e4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58b6588c51fe53098e5c6381356e30d6395fb2b99df5ec754d2867e71bc43e4b","first_computed_at":"2026-05-17T23:43:39.226537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:39.226537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ob0iXRvxssgyqxBNl2nJdiZJufKaLsx2U9ARGkwtJ+MNT08Yeh1pn1CowWcDMJpaq48BOOR8JzScXZCwarmkBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:39.227263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2b08bb336e2721a5903b99176d504c619d320fe48486ba86691237f44f10f78","sha256:53e985cf8fd48ab6198f9f99f6df94a5886e49722c2ef220fe55d9ca3973cc7a"],"state_sha256":"d70a8d914f9d97dabab71f2282f461b93354cdf120a18830224d5ffd8f7c5f01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iX4zODnXC+4Uo4ddiF4d+OhjbpSz/+iii/63BLvH0b4Dt8rHdSp+HnpNMpWqmrRxVjn2+adfeKxBE9Eoy/CvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:38:58.844206Z","bundle_sha256":"cae5d44a764d4fb83e81ed3305ca0a94ff4f122bddbbe183d5915c63fb4e97f2"}}