{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:E5X66VNCJ3PKKHRAVF5BHKRP2T","short_pith_number":"pith:E5X66VNC","canonical_record":{"source":{"id":"1910.02826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T14:40:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1168b2ba4c0adaa1aecbe8515d62a8f553189f6d3541d4589626e80c319c203c","abstract_canon_sha256":"9a89b45248bc5bc09f698665cb75d230d2fc38a22bd9d99d89e91fdac6963345"},"schema_version":"1.0"},"canonical_sha256":"276fef55a24edea51e20a97a13aa2fd4e6a8536bbedf93012e63894320c071d3","source":{"kind":"arxiv","id":"1910.02826","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02826","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02826v1","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02826","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"E5X66VNCJ3PK","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"E5X66VNCJ3PKKHRA","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"E5X66VNC","created_at":"2026-07-05T00:10:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:E5X66VNCJ3PKKHRAVF5BHKRP2T","target":"record","payload":{"canonical_record":{"source":{"id":"1910.02826","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T14:40:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1168b2ba4c0adaa1aecbe8515d62a8f553189f6d3541d4589626e80c319c203c","abstract_canon_sha256":"9a89b45248bc5bc09f698665cb75d230d2fc38a22bd9d99d89e91fdac6963345"},"schema_version":"1.0"},"canonical_sha256":"276fef55a24edea51e20a97a13aa2fd4e6a8536bbedf93012e63894320c071d3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:11.815152Z","signature_b64":"86wlFXIjnoi9DyiI0qGKuvwTlAaKqWykGhx0M59nCC71ZstTE7GaKFqtCIN1Ro743+PJkMdmYPaZoQkcgvdTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"276fef55a24edea51e20a97a13aa2fd4e6a8536bbedf93012e63894320c071d3","last_reissued_at":"2026-07-05T00:10:11.814813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:11.814813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.02826","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":"2026-07-05T00:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1UZh4w/0/9OL1IYbpks4cLEBnJ6XA1AKzb697AvpXVUyokMEqQP61h2/NKufgcWbBZZ1c4bcRqruuJ81TwOvAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:20:33.731583Z"},"content_sha256":"3e924623bac04f9a6a7a01eab623896d7c3190d8cf6edf45f11d9df28b2009d0","schema_version":"1.0","event_id":"sha256:3e924623bac04f9a6a7a01eab623896d7c3190d8cf6edf45f11d9df28b2009d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:E5X66VNCJ3PKKHRAVF5BHKRP2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-Paced Contextual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Boris Belousov, Hany Abdulsamad, Jan Peters, Pascal Klink","submitted_at":"2019-10-07T14:40:53Z","abstract_excerpt":"Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of environments from an unknown, uncontrolled context distribution, thus missing the benefits of structured, sequential learning. We introduce a novel relative entropy reinforcement learning algorithm that gives the agent the freedom to control the intermediate task distribution, allowing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02826","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/1910.02826/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":"2026-07-05T00:10:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UaUJbTYqvYxKmuLhHPprJeoqdFOgw4Wk56OTb+weVqzG60v9gY/wmeqiOAnI9xl/IIYUYwt/rz+PpNp2a9IHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:20:33.732069Z"},"content_sha256":"2ee1a872f5ab6aa390abcfa3d41193de35291c9324a03ca562a312e39179f0ff","schema_version":"1.0","event_id":"sha256:2ee1a872f5ab6aa390abcfa3d41193de35291c9324a03ca562a312e39179f0ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/bundle.json","state_url":"https://pith.science/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/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":"2026-08-04T13:20:33Z","links":{"resolver":"https://pith.science/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T","bundle":"https://pith.science/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/bundle.json","state":"https://pith.science/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E5X66VNCJ3PKKHRAVF5BHKRP2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:E5X66VNCJ3PKKHRAVF5BHKRP2T","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":"9a89b45248bc5bc09f698665cb75d230d2fc38a22bd9d99d89e91fdac6963345","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T14:40:53Z","title_canon_sha256":"1168b2ba4c0adaa1aecbe8515d62a8f553189f6d3541d4589626e80c319c203c"},"schema_version":"1.0","source":{"id":"1910.02826","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02826","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02826v1","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02826","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_12","alias_value":"E5X66VNCJ3PK","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_16","alias_value":"E5X66VNCJ3PKKHRA","created_at":"2026-07-05T00:10:11Z"},{"alias_kind":"pith_short_8","alias_value":"E5X66VNC","created_at":"2026-07-05T00:10:11Z"}],"graph_snapshots":[{"event_id":"sha256:2ee1a872f5ab6aa390abcfa3d41193de35291c9324a03ca562a312e39179f0ff","target":"graph","created_at":"2026-07-05T00:10:11Z","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/1910.02826/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of behaviors across related tasks, it generally relies on uninformed sampling of environments from an unknown, uncontrolled context distribution, thus missing the benefits of structured, sequential learning. We introduce a novel relative entropy reinforcement learning algorithm that gives the agent the freedom to control the intermediate task distribution, allowing ","authors_text":"Boris Belousov, Hany Abdulsamad, Jan Peters, Pascal Klink","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T14:40:53Z","title":"Self-Paced Contextual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02826","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":"sha256:3e924623bac04f9a6a7a01eab623896d7c3190d8cf6edf45f11d9df28b2009d0","target":"record","created_at":"2026-07-05T00:10:11Z","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":"9a89b45248bc5bc09f698665cb75d230d2fc38a22bd9d99d89e91fdac6963345","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-07T14:40:53Z","title_canon_sha256":"1168b2ba4c0adaa1aecbe8515d62a8f553189f6d3541d4589626e80c319c203c"},"schema_version":"1.0","source":{"id":"1910.02826","kind":"arxiv","version":1}},"canonical_sha256":"276fef55a24edea51e20a97a13aa2fd4e6a8536bbedf93012e63894320c071d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"276fef55a24edea51e20a97a13aa2fd4e6a8536bbedf93012e63894320c071d3","first_computed_at":"2026-07-05T00:10:11.814813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:11.814813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"86wlFXIjnoi9DyiI0qGKuvwTlAaKqWykGhx0M59nCC71ZstTE7GaKFqtCIN1Ro743+PJkMdmYPaZoQkcgvdTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:11.815152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.02826","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e924623bac04f9a6a7a01eab623896d7c3190d8cf6edf45f11d9df28b2009d0","sha256:2ee1a872f5ab6aa390abcfa3d41193de35291c9324a03ca562a312e39179f0ff"],"state_sha256":"8dd25540d3b07c21c86924440fb18fa2ee4b5430b9d08119c37c0447397da58d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvGCERKOmsWdniRmhPtKjEzL3jDU6Z/Ma/O9be9NUsmdOiRnluzzHStKPrtRnh5sUxlOSJUn2m0SHCm69nmzCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:20:33.736325Z","bundle_sha256":"70ef183c8d307d9216e3068cca123e72fad146e50ad030f4bb904005683bb191"}}