{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YVVHEVN7AV77FPFMLR65T2BOBQ","short_pith_number":"pith:YVVHEVN7","canonical_record":{"source":{"id":"1809.04506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T15:12:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"25a9a081a80ff0fbcac6f19ed781d8f52b495541d0047f77b641c947262e6ad3","abstract_canon_sha256":"1752b21523d3f00bfbebb35d681d290f0dec613b20cf2ee8566897dbcf917061"},"schema_version":"1.0"},"canonical_sha256":"c56a7255bf057ff2bcac5c7dd9e82e0c1cf58ed6f43b051c0741088fab4be487","source":{"kind":"arxiv","id":"1809.04506","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04506","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04506v2","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04506","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"YVVHEVN7AV77","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YVVHEVN7AV77FPFM","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YVVHEVN7","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YVVHEVN7AV77FPFMLR65T2BOBQ","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04506","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T15:12:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"25a9a081a80ff0fbcac6f19ed781d8f52b495541d0047f77b641c947262e6ad3","abstract_canon_sha256":"1752b21523d3f00bfbebb35d681d290f0dec613b20cf2ee8566897dbcf917061"},"schema_version":"1.0"},"canonical_sha256":"c56a7255bf057ff2bcac5c7dd9e82e0c1cf58ed6f43b051c0741088fab4be487","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:29.667236Z","signature_b64":"4qg/zIrpjJZBd491o0Oj0tsBMC2Qrx7JA8kIv25F+jBrVRXCxi41jp64yN5vGGJaBsU/wurDUwh6G6Qy1r3rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c56a7255bf057ff2bcac5c7dd9e82e0c1cf58ed6f43b051c0741088fab4be487","last_reissued_at":"2026-05-18T00:00:29.666805Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:29.666805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04506","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":"2026-05-18T00:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQi56MANEGpFLvCzwbWTTn4KZUvNI24IUW++djiicbsmVYV7ITR5RJ1lZNEuRmRjGBCr5vIIRur+hLJ9dsK9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:23:03.514377Z"},"content_sha256":"dfef588f8932dd36c1842816048fb5481a35c5631b9f6f9461aadfd30bc34b71","schema_version":"1.0","event_id":"sha256:dfef588f8932dd36c1842816048fb5481a35c5631b9f6f9461aadfd30bc34b71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YVVHEVN7AV77FPFMLR65T2BOBQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combined Reinforcement Learning via Abstract Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Joelle Pineau, Vincent Fran\\c{c}ois-Lavet, Yoshua Bengio","submitted_at":"2018-09-12T15:12:49Z","abstract_excerpt":"In the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04506","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":"2026-05-18T00:00:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jA/zlPewPuL44gsIpawE2+iPdA3DvATQHcUH5a0t4/ThkGkyXTfvRPuqw6BNrWRIpz03mDiRxIxGWyMg2oZlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:23:03.515016Z"},"content_sha256":"48f00d6449335b873a81c0f57d88dabb4bca3428997b4af2fcdc68bf0d676667","schema_version":"1.0","event_id":"sha256:48f00d6449335b873a81c0f57d88dabb4bca3428997b4af2fcdc68bf0d676667"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/bundle.json","state_url":"https://pith.science/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/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":"2026-05-25T09:23:03Z","links":{"resolver":"https://pith.science/pith/YVVHEVN7AV77FPFMLR65T2BOBQ","bundle":"https://pith.science/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/bundle.json","state":"https://pith.science/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVVHEVN7AV77FPFMLR65T2BOBQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YVVHEVN7AV77FPFMLR65T2BOBQ","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":"1752b21523d3f00bfbebb35d681d290f0dec613b20cf2ee8566897dbcf917061","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T15:12:49Z","title_canon_sha256":"25a9a081a80ff0fbcac6f19ed781d8f52b495541d0047f77b641c947262e6ad3"},"schema_version":"1.0","source":{"id":"1809.04506","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04506","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04506v2","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04506","created_at":"2026-05-18T00:00:29Z"},{"alias_kind":"pith_short_12","alias_value":"YVVHEVN7AV77","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YVVHEVN7AV77FPFM","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YVVHEVN7","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:48f00d6449335b873a81c0f57d88dabb4bca3428997b4af2fcdc68bf0d676667","target":"graph","created_at":"2026-05-18T00:00:29Z","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 the quest for efficient and robust reinforcement learning methods, both model-free and model-based approaches offer advantages. In this paper we propose a new way of explicitly bridging both approaches via a shared low-dimensional learned encoding of the environment, meant to capture summarizing abstractions. We show that the modularity brought by this approach leads to good generalization while being computationally efficient, with planning happening in a smaller latent state space. In addition, this approach recovers a sufficient low-dimensional representation of the environment, which op","authors_text":"Doina Precup, Joelle Pineau, Vincent Fran\\c{c}ois-Lavet, Yoshua Bengio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T15:12:49Z","title":"Combined Reinforcement Learning via Abstract Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04506","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:dfef588f8932dd36c1842816048fb5481a35c5631b9f6f9461aadfd30bc34b71","target":"record","created_at":"2026-05-18T00:00:29Z","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":"1752b21523d3f00bfbebb35d681d290f0dec613b20cf2ee8566897dbcf917061","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-12T15:12:49Z","title_canon_sha256":"25a9a081a80ff0fbcac6f19ed781d8f52b495541d0047f77b641c947262e6ad3"},"schema_version":"1.0","source":{"id":"1809.04506","kind":"arxiv","version":2}},"canonical_sha256":"c56a7255bf057ff2bcac5c7dd9e82e0c1cf58ed6f43b051c0741088fab4be487","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c56a7255bf057ff2bcac5c7dd9e82e0c1cf58ed6f43b051c0741088fab4be487","first_computed_at":"2026-05-18T00:00:29.666805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:29.666805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4qg/zIrpjJZBd491o0Oj0tsBMC2Qrx7JA8kIv25F+jBrVRXCxi41jp64yN5vGGJaBsU/wurDUwh6G6Qy1r3rDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:29.667236Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04506","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfef588f8932dd36c1842816048fb5481a35c5631b9f6f9461aadfd30bc34b71","sha256:48f00d6449335b873a81c0f57d88dabb4bca3428997b4af2fcdc68bf0d676667"],"state_sha256":"33bea1c7dd4cd205cd775ee9b4aac0ebaca3c17876fa2e58c48e2aed63666ced"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/M9C34FDTHxXhbMgojM2XDi3tDIgqi6EPzm6DNzg4EvCmxJM13ZGYJidY5X4AoxZeiy+Q15/YNf7GwQ7i4zqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:23:03.517505Z","bundle_sha256":"b8b4f77f2bc3b5433c16c8b0efc2c875181c34019ad321d6dc9eda3cb5206196"}}