{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SX6R7EHLZVMV2JPBGGTN7YU3WW","short_pith_number":"pith:SX6R7EHL","canonical_record":{"source":{"id":"1906.09223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:12:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"895393232a3619032f6db88542957db1a4f0097f90661a01509b068e0faced92","abstract_canon_sha256":"06532776884aabae5d2a2383991b8ea5d2dd0c798aca575564556a0b2b7a7291"},"schema_version":"1.0"},"canonical_sha256":"95fd1f90ebcd595d25e131a6dfe29bb58bee1a547efcb41e4ef12fabc083752c","source":{"kind":"arxiv","id":"1906.09223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09223","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09223v1","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09223","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"SX6R7EHLZVMV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SX6R7EHLZVMV2JPB","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SX6R7EHL","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SX6R7EHLZVMV2JPBGGTN7YU3WW","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09223","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:12:15Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"895393232a3619032f6db88542957db1a4f0097f90661a01509b068e0faced92","abstract_canon_sha256":"06532776884aabae5d2a2383991b8ea5d2dd0c798aca575564556a0b2b7a7291"},"schema_version":"1.0"},"canonical_sha256":"95fd1f90ebcd595d25e131a6dfe29bb58bee1a547efcb41e4ef12fabc083752c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:44.101530Z","signature_b64":"ctKmFWjjQdBihZUfu2PZOQuWB/MXyP8dw5NJ5Z6fqGxMY+Ehxu4MYUlQkY97m+H3CBY254bmFhQY5GyZVoesBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95fd1f90ebcd595d25e131a6dfe29bb58bee1a547efcb41e4ef12fabc083752c","last_reissued_at":"2026-05-17T23:42:44.100825Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:44.100825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09223","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":"2026-05-17T23:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWOtiUOn/Uii+pYqrRJdNc0e++jk1EYO6rWkq+lUcW8XAC312RbGrfdaWxtItEeYbBu+ArFkYrHQ0RfLJpTRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:40.227260Z"},"content_sha256":"c8060c09112e72ca93a70ba4f9d7a5fd8fc6326371a2eef437ef6fb799115ff4","schema_version":"1.0","event_id":"sha256:c8060c09112e72ca93a70ba4f9d7a5fd8fc6326371a2eef437ef6fb799115ff4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SX6R7EHLZVMV2JPBGGTN7YU3WW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangled Skill Embeddings for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Janith C. Petangoda, Jordi Grau-Moya, Peter Vrancx, Sergio Pascual-Diaz, Vincent Adam","submitted_at":"2019-06-21T16:12:15Z","abstract_excerpt":"We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal conditions, and by task-specific latent-space embeddings that allow for specialization to particular tasks. We show how the latent-spaces enable generalization to unseen dynamics and goals conditions. Additionally, policies equipped with such embeddings serve as a space of skills (or o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09223","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":"2026-05-17T23:42:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UvZHrLM3KAyKF+TO/s2wDRPbpwlF1B8km3LkmQW/q9YolLsZ7Sa9Gc0HVEjgHXCLA9/HjheLb1kOehTu801DAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:40.227908Z"},"content_sha256":"2a6636dc992c754c8acd97b8d7f01cbf9a396f1df09279023708022776b3536b","schema_version":"1.0","event_id":"sha256:2a6636dc992c754c8acd97b8d7f01cbf9a396f1df09279023708022776b3536b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/bundle.json","state_url":"https://pith.science/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/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":"2026-05-26T10:45:40Z","links":{"resolver":"https://pith.science/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW","bundle":"https://pith.science/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/bundle.json","state":"https://pith.science/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX6R7EHLZVMV2JPBGGTN7YU3WW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SX6R7EHLZVMV2JPBGGTN7YU3WW","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":"06532776884aabae5d2a2383991b8ea5d2dd0c798aca575564556a0b2b7a7291","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:12:15Z","title_canon_sha256":"895393232a3619032f6db88542957db1a4f0097f90661a01509b068e0faced92"},"schema_version":"1.0","source":{"id":"1906.09223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09223","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09223v1","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09223","created_at":"2026-05-17T23:42:44Z"},{"alias_kind":"pith_short_12","alias_value":"SX6R7EHLZVMV","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SX6R7EHLZVMV2JPB","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SX6R7EHL","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:2a6636dc992c754c8acd97b8d7f01cbf9a396f1df09279023708022776b3536b","target":"graph","created_at":"2026-05-17T23:42:44Z","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":"We propose a novel framework for multi-task reinforcement learning (MTRL). Using a variational inference formulation, we learn policies that generalize across both changing dynamics and goals. The resulting policies are parametrized by shared parameters that allow for transfer between different dynamics and goal conditions, and by task-specific latent-space embeddings that allow for specialization to particular tasks. We show how the latent-spaces enable generalization to unseen dynamics and goals conditions. Additionally, policies equipped with such embeddings serve as a space of skills (or o","authors_text":"Janith C. Petangoda, Jordi Grau-Moya, Peter Vrancx, Sergio Pascual-Diaz, Vincent Adam","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:12:15Z","title":"Disentangled Skill Embeddings for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09223","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:c8060c09112e72ca93a70ba4f9d7a5fd8fc6326371a2eef437ef6fb799115ff4","target":"record","created_at":"2026-05-17T23:42:44Z","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":"06532776884aabae5d2a2383991b8ea5d2dd0c798aca575564556a0b2b7a7291","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T16:12:15Z","title_canon_sha256":"895393232a3619032f6db88542957db1a4f0097f90661a01509b068e0faced92"},"schema_version":"1.0","source":{"id":"1906.09223","kind":"arxiv","version":1}},"canonical_sha256":"95fd1f90ebcd595d25e131a6dfe29bb58bee1a547efcb41e4ef12fabc083752c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fd1f90ebcd595d25e131a6dfe29bb58bee1a547efcb41e4ef12fabc083752c","first_computed_at":"2026-05-17T23:42:44.100825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:44.100825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ctKmFWjjQdBihZUfu2PZOQuWB/MXyP8dw5NJ5Z6fqGxMY+Ehxu4MYUlQkY97m+H3CBY254bmFhQY5GyZVoesBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:44.101530Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8060c09112e72ca93a70ba4f9d7a5fd8fc6326371a2eef437ef6fb799115ff4","sha256:2a6636dc992c754c8acd97b8d7f01cbf9a396f1df09279023708022776b3536b"],"state_sha256":"c35d0936d378916fa184a6c27eb05fe0e4c35c3b4a01d5b0c079b0a8e38d8977"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tqjt+E5e9veADAfRHZpoOyAsB+gLctvDP8fzjTvoRYMbvYpQhsTqP0+CAcK7AMqdHBV8a3NicK6I4y1m2+S+BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:45:40.231554Z","bundle_sha256":"7bed34c7fc9a1579b2a851cf779960985f659a1609d280d0a77e9021e8a0f11f"}}