{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:H3HOSIHN3TRFJMPJMAWLJD3NU6","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":"36d427bcce1da668892f82e65498b028bc7467d15003aed9581304f92d86327c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:12:42Z","title_canon_sha256":"5eb655521de8b52b683364564931c7cd08a6d2e61d2cecfd271c82f1e8471e25"},"schema_version":"1.0","source":{"id":"1907.05855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.05855","created_at":"2026-05-17T23:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"1907.05855v1","created_at":"2026-05-17T23:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05855","created_at":"2026-05-17T23:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"H3HOSIHN3TRF","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"H3HOSIHN3TRFJMPJ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"H3HOSIHN","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:021c2a4c8495fa26f218dbaa4542c25124ecc1280b441bc5e1e51687d13d292a","target":"graph","created_at":"2026-05-17T23:40:44Z","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 multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-","authors_text":"David Filliat, Guanghang Cai, Hugo Caselles-Dupr\\'e, Natalia D\\'iaz-Rodr\\'iguez, Ren\\'e Traor\\'e, Te Sun, Timoth\\'ee Lesort","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:12:42Z","title":"DisCoRL: Continual Reinforcement Learning via Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05855","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":"sha256:2c1a7b8b4088ff87d6a629b3b7277437c91e5e85920e3815e3c5da7608da43ff","target":"record","created_at":"2026-05-17T23:40:44Z","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":"36d427bcce1da668892f82e65498b028bc7467d15003aed9581304f92d86327c","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-11T09:12:42Z","title_canon_sha256":"5eb655521de8b52b683364564931c7cd08a6d2e61d2cecfd271c82f1e8471e25"},"schema_version":"1.0","source":{"id":"1907.05855","kind":"arxiv","version":1}},"canonical_sha256":"3ecee920eddce254b1e9602cb48f6da79e51c6ed4ba8ed731784ac5365ebd25d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ecee920eddce254b1e9602cb48f6da79e51c6ed4ba8ed731784ac5365ebd25d","first_computed_at":"2026-05-17T23:40:44.154239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:44.154239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+cSkMCjORMA7+F6dsVchiOuQ5dLJs/ynzURrXoDAqCBxz0xX9hywfeO6sXrhH5Hwl1tW/0sALqm1lZA7nEeBAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:44.154919Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.05855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c1a7b8b4088ff87d6a629b3b7277437c91e5e85920e3815e3c5da7608da43ff","sha256:021c2a4c8495fa26f218dbaa4542c25124ecc1280b441bc5e1e51687d13d292a"],"state_sha256":"b58c1f29f9dcfb7ce9a86d4f7c89f793d1d9a8ccf4443b9386587bdcfd7a3b8e"}